python program freezes when running for a few days - python

Here's the Problem:
I'm writing a python program that's purpose is to continuously collect news from RSS feeds. I want the program to collect the data for 1 week. The problem is that the program never makes it to the end of the week. Sometimes it freezes after running for several days, sometimes several hours and even just a few minutes. It always freezes, no errors. When I say freezing I mean the interpreter seems to still be running, in that I can't give it any additional commands. How can I solve this problem?
I'll post the code below. Thanks guys!!
from goose import Goose
from requests import get
import urllib2
import feedparser
from urllib2 import urlopen
import pandas as pd
import numpy as np
from bs4 import BeautifulSoup
import re
import datetime as dt
import time
import os
Symbols=['AAPL','T','BA','XOM','GOOG','JPM','PG','WMT']
url='http://finance.yahoo.com/rss/headline?s='
for t in xrange(7):
AAPL=pd.DataFrame()
AAPL['Published']=""
AAPL['Title']=""
AAPL['link']=""
AAPL['ID']=""
AAPL['News']=""
T=pd.DataFrame()
T['Published']=""
T['Title']=""
T['link']=""
T['ID']=""
T['News']=""
BA=pd.DataFrame()
BA['Published']=""
BA['Title']=""
BA['link']=""
BA['ID']=""
BA['News']=""
XOM=pd.DataFrame()
XOM['Published']=""
XOM['Title']=""
XOM['link']=""
XOM['ID']=""
XOM['News']=""
GOOG=pd.DataFrame()
GOOG['Published']=""
GOOG['Title']=""
GOOG['link']=""
GOOG['ID']=""
GOOG['News']=""
JPM=pd.DataFrame()
JPM['Published']=""
JPM['Title']=""
JPM['link']=""
JPM['ID']=""
JPM['News']=""
PG=pd.DataFrame()
PG['Published']=""
PG['Title']=""
PG['link']=""
PG['ID']=""
PG['News']=""
WMT=pd.DataFrame()
WMT['Published']=""
WMT['Title']=""
WMT['link']=""
WMT['ID']=""
WMT['News']=""
DaysIDsAAPL=[]
DaysIDsT=[]
DaysIDsBA=[]
DaysIDsXOM=[]
DaysIDsGOOG=[]
DaysIDsJPM=[]
DaysIDsPG=[]
DaysIDsWMT=[]
count=0
AAPLCount=0
TCount=0
BACount=0
XOMCount=0
GOOGCount=0
JPMCount=0
PGCount=0
WMTCount=0
date=dt.date.today()
newpathAAPL = r'D:\News Data\AAPL\\'+str(t)
newpathT = r'D:\News Data\T\\'+str(t)
newpathBA = r'D:\News Data\BA\\'+str(t)
newpathXOM = r'D:\News Data\XOM\\'+str(t)
newpathGOOG = r'D:\News Data\GOOG\\'+str(t)
newpathJPM = r'D:\News Data\JPM\\'+str(t)
newpathPG = r'D:\News Data\PG\\'+str(t)
newpathWMT = r'D:\News Data\WMT\\'+str(t)
os.makedirs(newpathAAPL)
os.makedirs(newpathT)
os.makedirs(newpathBA)
os.makedirs(newpathXOM)
os.makedirs(newpathGOOG)
os.makedirs(newpathJPM)
os.makedirs(newpathPG)
os.makedirs(newpathWMT)
while dt.date.today()==date:
print "Loop"
try:
#AAPL inner most loop
d1=feedparser.parse(url+Symbols[0])
for x in xrange(len(d1['entries'])):
if int(d1.entries[x]['id'][14:]) not in DaysIDsAAPL:
DaysIDsAAPL.append(int(d1.entries[x]['id'][14:]))
y = len(AAPL.index.tolist())
m=re.search(r'\*(.*)',d1.entries[x]['link'])
z=re.search(r'\?ru=yahoo\?mod=yahoo_itp',m.group(1))
if type(z) is not None:
m=re.sub(r'\?ru=yahoo\?mod=yahoo_itp', '', m.group(1))
AAPL.loc[y,'Title'] =d1.entries[x]['title'].encode('utf8')
AAPL.loc[y,'link'] =m.encode('utf8')
AAPL.loc[y,'Published'] =d1.entries[x]['published'].encode('utf8')
AAPL.loc[y,'ID'] =int(d1.entries[x]['id'][14:])
hdr = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'}
page = get(m,headers=hdr)
extractor = Goose()
article = extractor.extract(raw_html=page.text)
text = article.cleaned_text.encode('utf8')
if text == '':
try:
url2 = m
req = urllib2.Request(url2, None, hdr)
html2 = urlopen(req).read().decode('utf8')
raw = BeautifulSoup(html2,"lxml").get_text().encode('utf8')
Text_file = open(newpathAAPL+r"\\"+str(AAPLCount)+".txt", "w")
Text_file.write(raw)
Text_file.close()
AAPL.loc[y,'News'] = AAPLCount
AAPLCount+=1
AAPL=AAPL.fillna("")
AAPL.to_csv(newpathAAPL+r'\Key.csv')
except:
print m
print "AAPL"
else:
Text_file = open(newpathAAPL+r"\\"+str(AAPLCount)+".txt", "w")
Text_file.write(text)
Text_file.close()
AAPL.loc[y,'News'] =AAPLCount
AAPLCount+=1
AAPL=AAPL.fillna("")
AAPL.to_csv(newpathAAPL+r'\Key.csv')
print "AAPL"
#T inner most loop
d2=feedparser.parse(url+Symbols[1])
for x in xrange(len(d2['entries'])):
if int(d2.entries[x]['id'][14:]) not in DaysIDsT:
DaysIDsT.append(int(d2.entries[x]['id'][14:]))
y = len(T.index.tolist())
m=re.search(r'\*(.*)',d2.entries[x]['link'])
z=re.search(r'\?ru=yahoo\?mod=yahoo_itp',m.group(1))
if type(z) is not None:
m=re.sub(r'\?ru=yahoo\?mod=yahoo_itp', '', m.group(1))
T.loc[y,'Title'] =d2.entries[x]['title'].encode('utf8')
T.loc[y,'link'] =m.encode('utf8')
T.loc[y,'Published'] =d2.entries[x]['published'].encode('utf8')
T.loc[y,'ID'] =int(d2.entries[x]['id'][14:])
hdr = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'}
page = get(m,headers=hdr)
extractor = Goose()
article = extractor.extract(raw_html=page.text)
text = article.cleaned_text.encode('utf8')
if text == '':
try:
url2 = m
req = urllib2.Request(url2, None, hdr)
html2 = urlopen(req).read().decode('utf8')
raw = BeautifulSoup(html2,"lxml").get_text().encode('utf8')
Text_file = open(newpathT+r"\\"+str(TCount)+".txt", "w")
Text_file.write(raw)
Text_file.close()
T.loc[y,'News'] = TCount
TCount+=1
T=T.fillna("")
T.to_csv(newpathT+r'\Key.csv')
except:
print m
print "T"
else:
Text_file = open(newpathT+r"\\"+str(TCount)+".txt", "w")
Text_file.write(text)
Text_file.close()
T.loc[y,'News'] =TCount
TCount+=1
T=T.fillna("")
T.to_csv(newpathT+r'\Key.csv')
print "T"
#BA inner most loop
d3=feedparser.parse(url+Symbols[2])
for x in xrange(len(d3['entries'])):
if int(d3.entries[x]['id'][14:]) not in DaysIDsBA:
DaysIDsBA.append(int(d3.entries[x]['id'][14:]))
y = len(BA.index.tolist())
m=re.search(r'\*(.*)',d3.entries[x]['link'])
z=re.search(r'\?ru=yahoo\?mod=yahoo_itp',m.group(1))
if type(z) is not None:
m=re.sub(r'\?ru=yahoo\?mod=yahoo_itp', '', m.group(1))
BA.loc[y,'Title'] =d3.entries[x]['title'].encode('utf8')
BA.loc[y,'link'] =m.encode('utf8')
BA.loc[y,'Published'] =d3.entries[x]['published'].encode('utf8')
BA.loc[y,'ID'] =int(d3.entries[x]['id'][14:])
hdr = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'}
page = get(m,headers=hdr)
extractor = Goose()
article = extractor.extract(raw_html=page.text)
text = article.cleaned_text.encode('utf8')
if text == '':
try:
url2 = m
req = urllib2.Request(url2, None, hdr)
html2 = urlopen(req).read().decode('utf8')
raw = BeautifulSoup(html2,"lxml").get_text().encode('utf8')
Text_file = open(newpathBA+r"\\"+str(BACount)+".txt", "w")
Text_file.write(raw)
Text_file.close()
BA.loc[y,'News'] = BACount
BACount+=1
BA=BA.fillna("")
BA.to_csv(newpathBA+r'\Key.csv')
except:
print m
print "BA"
else:
Text_file = open(newpathBA+r"\\"+str(BACount)+".txt", "w")
Text_file.write(text)
Text_file.close()
BA.loc[y,'News'] =BACount
BACount+=1
BA=BA.fillna("")
BA.to_csv(newpathBA+r'\Key.csv')
print "BA"
#XOM inner most loop
d4=feedparser.parse(url+Symbols[3])
for x in xrange(len(d4['entries'])):
if int(d4.entries[x]['id'][14:]) not in DaysIDsXOM:
DaysIDsXOM.append(int(d4.entries[x]['id'][14:]))
y = len(XOM.index.tolist())
m=re.search(r'\*(.*)',d4.entries[x]['link'])
z=re.search(r'\?ru=yahoo\?mod=yahoo_itp',m.group(1))
if type(z) is not None:
m=re.sub(r'\?ru=yahoo\?mod=yahoo_itp', '', m.group(1))
XOM.loc[y,'Title'] =d4.entries[x]['title'].encode('utf8')
XOM.loc[y,'link'] =m.encode('utf8')
XOM.loc[y,'Published'] =d4.entries[x]['published'].encode('utf8')
XOM.loc[y,'ID'] =int(d4.entries[x]['id'][14:])
hdr = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'}
page = get(m,headers=hdr)
extractor = Goose()
article = extractor.extract(raw_html=page.text)
text = article.cleaned_text.encode('utf8')
if text == '':
try:
url2 = m
req = urllib2.Request(url2, None, hdr)
html2 = urlopen(req).read().decode('utf8')
raw = BeautifulSoup(html2,"lxml").get_text().encode('utf8')
Text_file = open(newpathXOM+r"\\"+str(XOMCount)+".txt", "w")
Text_file.write(raw)
Text_file.close()
XOM.loc[y,'News'] = XOMCount
XOMCount+=1
XOM=XOM.fillna("")
XOM.to_csv(newpathXOM+r'\Key.csv')
except:
print m
print "XOM"
else:
Text_file = open(newpathXOM+r"\\"+str(XOMCount)+".txt", "w")
Text_file.write(text)
Text_file.close()
XOM.loc[y,'News'] =XOMCount
XOMCount+=1
XOM=XOM.fillna("")
XOM.to_csv(newpathXOM+r'\Key.csv')
#GOOG inner most loop
d5=feedparser.parse(url+Symbols[4])
for x in xrange(len(d5['entries'])):
if int(d5.entries[x]['id'][14:]) not in DaysIDsGOOG:
DaysIDsGOOG.append(int(d5.entries[x]['id'][14:]))
y = len(GOOG.index.tolist())
m=re.search(r'\*(.*)',d5.entries[x]['link'])
z=re.search(r'\?ru=yahoo\?mod=yahoo_itp',m.group(1))
if type(z) is not None:
m=re.sub(r'\?ru=yahoo\?mod=yahoo_itp', '', m.group(1))
GOOG.loc[y,'Title'] =d5.entries[x]['title'].encode('utf8')
GOOG.loc[y,'link'] =m.encode('utf8')
GOOG.loc[y,'Published'] =d5.entries[x]['published'].encode('utf8')
GOOG.loc[y,'ID'] =int(d5.entries[x]['id'][14:])
hdr = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'}
page = get(m,headers=hdr)
extractor = Goose()
article = extractor.extract(raw_html=page.text)
text = article.cleaned_text.encode('utf8')
if text == '':
try:
url2 = m
req = urllib2.Request(url2, None, hdr)
html2 = urlopen(req).read().decode('utf8')
raw = BeautifulSoup(html2,"lxml").get_text().encode('utf8')
Text_file = open(newpathGOOG+r"\\"+str(GOOGCount)+".txt", "w")
Text_file.write(raw)
Text_file.close()
GOOG.loc[y,'News'] = GOOGCount
GOOGCount+=1
GOOG=GOOG.fillna("")
GOOG.to_csv(newpathGOOG+r'\Key.csv')
except:
print m
print "GOOG"
else:
Text_file = open(newpathGOOG+r"\\"+str(GOOGCount)+".txt", "w")
Text_file.write(text)
Text_file.close()
GOOG.loc[y,'News'] =GOOGCount
GOOGCount+=1
GOOG=GOOG.fillna("")
GOOG.to_csv(newpathGOOG+r'\Key.csv')
print "GOOG"
#JPM inner most loop
d6=feedparser.parse(url+Symbols[5])
for x in xrange(len(d6['entries'])):
if int(d6.entries[x]['id'][14:]) not in DaysIDsJPM:
DaysIDsJPM.append(int(d6.entries[x]['id'][14:]))
y = len(JPM.index.tolist())
m=re.search(r'\*(.*)',d6.entries[x]['link'])
z=re.search(r'\?ru=yahoo\?mod=yahoo_itp',m.group(1))
if type(z) is not None:
m=re.sub(r'\?ru=yahoo\?mod=yahoo_itp', '', m.group(1))
JPM.loc[y,'Title'] =d6.entries[x]['title'].encode('utf8')
JPM.loc[y,'link'] =m.encode('utf8')
JPM.loc[y,'Published'] =d6.entries[x]['published'].encode('utf8')
JPM.loc[y,'ID'] =int(d6.entries[x]['id'][14:])
hdr = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'}
page = get(m,headers=hdr)
extractor = Goose()
article = extractor.extract(raw_html=page.text)
text = article.cleaned_text.encode('utf8')
if text == '':
try:
url2 = m
req = urllib2.Request(url2, None, hdr)
html2 = urlopen(req).read().decode('utf8')
raw = BeautifulSoup(html2,"lxml").get_text().encode('utf8')
Text_file = open(newpathJPM+r"\\"+str(JPMCount)+".txt", "w")
Text_file.write(raw)
Text_file.close()
JPM.loc[y,'News'] = JPMCount
JPMCount+=1
JPM=JPM.fillna("")
JPM.to_csv(newpathJPM+r'\Key.csv')
except:
print m
print "JPM"
else:
Text_file = open(newpathJPM+r"\\"+str(JPMCount)+".txt", "w")
Text_file.write(text)
Text_file.close()
JPM.loc[y,'News'] =JPMCount
JPMCount+=1
JPM=JPM.fillna("")
JPM.to_csv(newpathJPM+r'\Key.csv')
print "JPM"
#PG inner most loop
d7=feedparser.parse(url+Symbols[6])
for x in xrange(len(d7['entries'])):
if int(d7.entries[x]['id'][14:]) not in DaysIDsPG:
DaysIDsPG.append(int(d7.entries[x]['id'][14:]))
y = len(PG.index.tolist())
m=re.search(r'\*(.*)',d7.entries[x]['link'])
z=re.search(r'\?ru=yahoo\?mod=yahoo_itp',m.group(1))
if type(z) is not None:
m=re.sub(r'\?ru=yahoo\?mod=yahoo_itp', '', m.group(1))
PG.loc[y,'Title'] =d7.entries[x]['title'].encode('utf8')
PG.loc[y,'link'] =m.encode('utf8')
PG.loc[y,'Published'] =d7.entries[x]['published'].encode('utf8')
PG.loc[y,'ID'] =int(d7.entries[x]['id'][14:])
hdr = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'}
page = get(m,headers=hdr)
extractor = Goose()
article = extractor.extract(raw_html=page.text)
text = article.cleaned_text.encode('utf8')
if text == "":
try:
url2 = m
req = urllib2.Request(url2, None, hdr)
html2 = urlopen(req).read().decode('utf8')
raw = BeautifulSoup(html2,"lxml").get_text().encode('utf8')
Text_file = open(newpathPG+r"\\"+str(PGCount)+".txt", "w")
Text_file.write(raw)
Text_file.close()
PG.loc[y,'News'] = PGCount
PGCount+=1
PG=PG.fillna("")
PG.to_csv(newpathPG+r'\Key.csv')
except:
print m
print "PG"
else:
Text_file = open(newpathPG+r"\\"+str(PGCount)+".txt", "w")
Text_file.write(text)
Text_file.close()
PG.loc[y,'News'] =PGCount
PGCount+=1
PG=PG.fillna("")
PG.to_csv(newpathPG+r'\Key.csv')
print "PG"
#WMT inner most loop
d8=feedparser.parse(url+Symbols[7])
for x in xrange(len(d8['entries'])):
if int(d8.entries[x]['id'][14:]) not in DaysIDsWMT:
DaysIDsWMT.append(int(d8.entries[x]['id'][14:]))
y = len(WMT.index.tolist())
m=re.search(r'\*(.*)',d8.entries[x]['link'])
z=re.search(r'\?ru=yahoo\?mod=yahoo_itp',m.group(1))
if type(z) is not None:
m=re.sub(r'\?ru=yahoo\?mod=yahoo_itp', '', m.group(1))
WMT.loc[y,'Title'] =d8.entries[x]['title'].encode('utf8')
WMT.loc[y,'link'] =m.encode('utf8')
WMT.loc[y,'Published'] =d8.entries[x]['published'].encode('utf8')
WMT.loc[y,'ID'] =int(d8.entries[x]['id'][14:])
hdr = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'}
page = get(m,headers=hdr)
extractor = Goose()
article = extractor.extract(raw_html=page.text)
text = article.cleaned_text.encode('utf8')
if text == "":
try:
url2 = m
req = urllib2.Request(url2, None, hdr)
html2 = urlopen(req).read().decode('utf8')
raw = BeautifulSoup(html2,"lxml").get_text().encode('utf8')
Text_file = open(newpathWMT+r"\\"+str(WMTCount)+".txt", "w")
Text_file.write(raw)
Text_file.close()
WMT.loc[y,'News'] = WMTCount
WMTCount+=1
WMT=WMT.fillna("")
WMT.to_csv(newpathWMT+r'\Key.csv')
except:
print m
print "WMT"
else:
Text_file = open(newpathWMT+r"\\"+str(WMTCount)+".txt", "w")
Text_file.write(text)
Text_file.close()
WMT.loc[y,'News'] =WMTCount
WMTCount+=1
WMT=WMT.fillna("")
WMT.to_csv(newpathWMT+r'\Key.csv')
print "WMT"
count+=1
print count
time.sleep(1)
except:
print "Error"
AAPL=AAPL.fillna("")
AAPL.to_csv(newpathAAPL+r'\Key.csv')
T=T.fillna("")
T.to_csv(newpathT+r'\Key.csv')
BA=BA.fillna("")
BA.to_csv(newpathBA+r'\Key.csv')
XOM=XOM.fillna("")
XOM.to_csv(newpathXOM+r'\Key.csv')
GOOG=GOOG.fillna("")
GOOG.to_csv(newpathGOOG+r'\Key.csv')
JPM=JPM.fillna("")
JPM.to_csv(newpathJPM+r'\Key.csv')
PG=PG.fillna("")
PG.to_csv(newpathPG+r'\Key.csv')
WMT=WMT.fillna("")
WMT.to_csv(newpathWMT+r'\Key.csv')


in the program is consumed too much RAM when it collects a too large of feeds or if there are other active processes on your system (this is why the time to freeze differs), see Why does a simple python script crash my system
The process in that your program runs stores the arrays and variables for the calculations in process memory which is ram
you can fix this by forcing the program to use hard disk memory.
For workarounds (shelve, periodically saving the collected feeds to a textfile (moves information from ram to rom and frees ram), ...) see the following links
memory usage, how to free memory
Python large variable RAM usage
I need to free up RAM by storing a Python dictionary on the hard drive, not in RAM. Is it possible?

Related

While loop stops working but the process continues running in python

I use a while loop in Python to download several pdf documents given by a csv file.
The code runs smoothly without any issue but the loop stops working after several loops (sometimes 100 other times 40 or 140).
Below is my code which is used:
import pandas as pd
import os
import urllib
from urllib import request
import requests
import csv
import numpy as np
df = pd.read_csv('Linklist.csv', sep = ';') # can also index sheet by name or fetch all sheets
df.head() #get relevant columns
url_list = df['URL'].tolist() #column with links
name_list = df['Name'].tolist() #column with name
name_list_2 =df['Year'].to_list() #column with second identifier here a year for example
Year_date = []
for element in name_list_2:
Year_date.append(str(element))
max_length = len(url_list)
i = 0
f = open('results.csv', 'w')
writer = csv.writer(f)
while i <= max_length-1:
response = requests.get(url_list[i])
opener = urllib.request.build_opener()
opener.addheaders = [('User-Agent', 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/15.0 Safari/605.1.15')]
if response.status_code != 200:
i += 1
a = str(response.status_code)
write_a = (name_list[i], Year_date[i], a)
writer.writerow(write_a)
print(name_list[i]+' '+ Year_date[i]+ ' ' +a)
else:
urllib.request.install_opener(opener)
request.urlretrieve( url_list[i],'/targetpath/'+ name_list[i] + Year_date[i] + '.pdf') #.pdf if it is a pdf doc you want to download
b = str(response.status_code)
write_b = (name_list[i], Year_date[i], b)
writer.writerow(write_b)
print(name_list[i]+' '+ Year_date[i] + ' '+ b)
i += 1
f.close()

The information by #barmar and #ogdenkev is correct I needed to integrate a Timeout component!
The working code looks like this now (just integrated the part which I changed):
DEFAULT_TIMEOUT = 180
old_send = requests.Session.send
def new_send(*args, **kwargs):
if kwargs.get("timeout", None) is None:
kwargs["timeout"] = DEFAULT_TIMEOUT
return old_send(*args, **kwargs)
requests.Session.send = new_send
headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/15.0 Safari/605.1.15'}
while i <= max_length-1:
try:
response = requests.get(url_list[I], headers = headers)
opener = urllib.request.build_opener()
opener.addheaders = [('User-Agent', 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/15.0 Safari/605.1.15')]
if response.status_code != 200:
a = str(response.status_code)
write_a = (name_list[i], Year_date[i], a)
writer.writerow(write_a)
print(name_list[i]+' '+ Year_date[i]+ ' ' +a)
print(i)
i += 1
else:
urllib.request.install_opener(opener)
request.urlretrieve( url_list[i],'/path/'+ name_list[i] + Year_date[i] + '.pdf') #.pdf if it is a pdf doc you want to download
b = str(response.status_code)
write_b = (name_list[i], Year_date[i], b)
writer.writerow(write_b)
print(name_list[i]+' '+ Year_date[i] + ' '+ b)
print(i)
i += 1
except requests.exceptions.RequestException as e:
c = 'Timeout'
write_a = (name_list[i], Year_date[i], c)
writer.writerow(write_a)
print(name_list[i]+' '+ Year_date[i]+ ' ' +c)
print(i)
i += 1
f.close()

Scraper downloading and saving just 20 images

I am trying to download and save images using a scraper but it only downloads the first 20 images while I want it to download as many images as possible.
import requests
from bs4 import BeautifulSoup
import os
url = "https://www.google.com/search?q=cats&sxsrf=ALeKk01diaA8AhwZsRpiMkZxaTUY6MuN4Q:1624119375856&source=lnms&tbm=isch&sa=X&ved=2ahUKEwj62uGTjKTxAhWMIsAKHV12B74Q_AUoAXoECAEQAw&biw=1848&bih=949"
folder = "images"
r = requests.get(url,stream=True)
soup = BeautifulSoup(r.text,"html.parser")
images = soup.select("img")
try:
os.mkdir(os.path.join(os.getcwd(),folder))
except:
pass
os.chdir(os.path.join(os.getcwd(),folder))
i = 0
for image in images:
if i != 0:
link = image["src"]
with open(str(i) + ".jpg", "wb") as f:
im = requests.get(link)
f.write(im.content)
print("Writing: ",i)
i += 1

with this code i get 109 jpeg
import requests
from bs4 import BeautifulSoup
import os
my_UA="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36 OPR/58.0.3135.107"
headers = {}
headers['User-Agent'] = my_UA
url = "https://www.google.com/search?q=cats&sxsrf=ALeKk01diaA8AhwZsRpiMkZxaTUY6MuN4Q:1624119375856&source=lnms&tbm=isch&sa=X&ved=2ahUKEwj62uGTjKTxAhWMIsAKHV12B74Q_AUoAXoECAEQAw&biw=1848&bih=949"
folder = "images"
r = requests.get(url,stream=True,headers=headers)
soup = BeautifulSoup(r.text,"html.parser")
images = soup.select("img")
try:
os.mkdir(os.path.join(os.getcwd(),folder))
except:
pass
os.chdir(os.path.join(os.getcwd(),folder))
i = 0
print("total images found=",len(images))
for image in images:
link=""
if image.get("src"):
link = image["src"]
elif image.get("data-src"):
link = image["data-src"]
if link and not "image/gif;" in link:
with open(str(i) + ".jpg", "wb") as f:
im = requests.get(link,headers=headers)
f.write(im.content)
print("Writing: ",i)
i += 1
-there are 2 properties "src" and "data-src"
-It skips gifs.
-For more files you can do it with selenium for example

Resolve Python Module Error To Enable Web Scraping script?

Using stackoverflow for the first time trying to figure out how to scrape Yelp data and having a hard time. Have set up LXML, beautiful soup, requests, PIP, Python and have added these to the path in system variables yet I am still getting the error below when I try to run code below. Any suggestions?
File "test2.py", line 4, in
from exceptions import ValueError
ModuleNotFoundError: No module named 'exceptions'
from lxml import html
import json
import requests
from exceptions import ValueError
import re, urllib
import urllib3
import argparse
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
from requests.packages.urllib3.exceptions import InsecureRequestWarning
import time
from concurrent.futures import ThreadPoolExecutor
import sys
from threading import Thread
import os
requests.packages.urllib3.disable_warnings(InsecureRequestWarning)
#[#'https://www.yelp.com/biz/kdb-kitchen-den-bar-long-beach',
yelp_urls =['https://www.yelp.com/biz/the-atlas-room-washington','https://www.yelp.com/biz/the-rack-brandon','https://www.yelp.com/biz/payard-p%C3%A2tisserie-and-bistro-new-york-2','https://www.yelp.com/biz/maison-giraud-pacific-palisades','https://www.yelp.com/biz/saltbox-san-diego','https://www.yelp.com/biz/carmichaels-chicago-steak-house-chicago','https://www.yelp.com/biz/black-eyed-pea-restaurant-houston-6','https://www.yelp.com/biz/perfecto-mundo-latin-fusion-bistro-commack','https://www.yelp.com/biz/smittys-bbq-boyd','https://www.yelp.com/biz/reston-kabob-reston','https://www.yelp.com/biz/bookmark-cafe-largo','https://www.yelp.com/biz/the-tin-angel-pittsburgh','https://www.yelp.com/biz/briantos-original-hoagies-orlando','https://www.yelp.com/biz/freeway-diner-woodbury','https://www.yelp.com/biz/river-gods-cambridge','https://www.yelp.com/biz/golan-kosher-restaurant-north-hollywood-2','https://www.yelp.com/biz/city-hall-restaurant-new-york-2','https://www.yelp.com/biz/empire-pizza-and-grill-west-chester','https://www.yelp.com/biz/cityzen-washington-2','https://www.yelp.com/biz/three-degrees-los-gatos','https://www.yelp.com/biz/applebees-grill-bar-quakertown','https://www.yelp.com/biz/johnny-carinos-covina','https://www.yelp.com/biz/buffet-de-la-gare-hastings-hdsn','https://www.yelp.com/biz/continental-food-management-la-mirada','https://www.yelp.com/biz/elephant-bar-restaurant-peoria','https://www.yelp.com/biz/sullivans-steakhouse-denver','https://www.yelp.com/biz/yucatan-liquid-stand-coppell','https://www.yelp.com/biz/tomato-pie-morristown','https://www.yelp.com/biz/willett-house-port-chester','https://www.yelp.com/biz/thai-corner-san-antonio-2','https://www.yelp.com/biz/silkes-american-grill-mesa','https://www.yelp.com/biz/t-mex-cantina-fort-lauderdale-2','https://www.yelp.com/biz/casa-oaxaca-washington','https://www.yelp.com/biz/wings-on-wheels-hebron','https://www.yelp.com/biz/siris-thai-french-cuisine-cherry-hill','https://www.yelp.com/biz/nightwood-chicago','https://www.yelp.com/biz/cafe-gallery-burlington','https://www.yelp.com/biz/the-hurricane-caf%C3%A9-seattle-2','https://www.yelp.com/biz/231-ellsworth-san-mateo','https://www.yelp.com/biz/la-marmite-williston-park','https://www.yelp.com/biz/the-river-house-palm-beach-gardens-2','https://www.yelp.com/biz/langermanns-baltimore','https://www.yelp.com/biz/del-friscos-grille-phoenix','https://www.yelp.com/biz/carrows-family-restaurant-antioch','https://www.yelp.com/biz/minerva-fine-indian-herndon-va-herndon-5','https://www.yelp.com/biz/the-mason-bar-dallas','https://www.yelp.com/biz/la-cote-cafe-and-wine-bar-seattle','https://www.yelp.com/biz/vareli-new-york','https://www.yelp.com/biz/wendys-wixom','https://www.yelp.com/biz/lanterna-tuscan-bistro-nyack','https://www.yelp.com/biz/yo-taco-duxbury','https://www.yelp.com/biz/bombay-palace-new-york','https://www.yelp.com/biz/cafe-buonaros-naperville','https://www.yelp.com/biz/ponti-seafood-grill-seattle-3','https://www.yelp.com/biz/bill-johnsons-big-apple-restaurants-phoenix-5','https://www.yelp.com/biz/by-word-of-mouth-oakland-park','https://www.yelp.com/biz/anna-maries-pizza-and-restaurant-wharton','https://www.yelp.com/biz/dierdorf-and-harts-steakhouse-saint-louis','https://www.yelp.com/biz/wine-5-cafe-las-vegas','https://www.yelp.com/biz/ernies-restaurant-plymouth','https://www.yelp.com/biz/next-door-pizza-and-pub-lees-summit','https://www.yelp.com/biz/lannys-alta-cocina-mexicana-fort-worth','https://www.yelp.com/biz/jalisco-mexican-restaurant-eastlake','https://www.yelp.com/biz/clio-boston','https://www.yelp.com/biz/uncommon-grounds-aliquippa','https://www.yelp.com/biz/uozumi-restaurant-palmdale','https://www.yelp.com/biz/enzos-pizza-matawan','https://www.yelp.com/biz/the-pointe-cafe-south-san-francisco','https://www.yelp.com/biz/captains-restaurant-and-seafood-market-florida-city','https://www.yelp.com/biz/le-perigord-new-york-4','https://www.yelp.com/biz/i-love-thai-arlington','https://www.yelp.com/biz/bistro-44-bedford','https://www.yelp.com/biz/ritters-marietta','https://www.yelp.com/biz/rouge-et-blanc-new-york','https://www.yelp.com/biz/assembly-steak-house-and-seafood-grill-englewood-cliffs-2','https://www.yelp.com/biz/american-turkish-restaurant-fort-lauderdale','https://www.yelp.com/biz/r-and-r-bar-b-que-and-catering-service-missouri-2','https://www.yelp.com/biz/sushi-land-long-beach','https://www.yelp.com/biz/longshots-sports-bar-waretown','https://www.yelp.com/biz/salt-creek-barbeque-glendale-heights','https://www.yelp.com/biz/pizza-market-breese','https://www.yelp.com/biz/john-qs-steakhouse-cleveland','https://www.yelp.com/biz/bistro-n-boca-raton-2','https://www.yelp.com/biz/samanthas-restaurant-silver-spring-2','https://www.yelp.com/biz/baha-brothers-sandbar-grill-taunton-3','https://www.yelp.com/biz/cafe-cortina-farmington-hills-5','https://www.yelp.com/biz/big-beaver-tavern-troy','https://www.yelp.com/biz/hogans-restaurant-bloomfield-hills','https://www.yelp.com/biz/the-copper-monkey-beaverton','https://www.yelp.com/biz/clement-street-bar-and-grill-san-francisco','https://www.yelp.com/biz/pepin-scottsdale','https://www.yelp.com/biz/village-belle-philadelphia','https://www.yelp.com/biz/sweet-woodruff-san-francisco','https://www.yelp.com/biz/siam-marina-tinley-park','https://www.yelp.com/biz/luigis-italian-restaurant-centennial-2','https://www.yelp.com/biz/smokin-wills-barbecue-roselle','https://www.yelp.com/biz/voltaire-restaurant-scottsdale','https://www.yelp.com/biz/jus-cookins-restaurant-lakewood-2','https://www.yelp.com/biz/pegs-countryside-cafe-hamel','https://www.yelp.com/biz/rays-grill-fulshear','https://www.yelp.com/biz/cafe-zalute-rosemont','https://www.yelp.com/biz/guard-house-inn-gladwyne','https://www.yelp.com/biz/road-runner-grand-canyon-las-vegas-2','https://www.yelp.com/biz/garage-restaurant-and-cafe-new-york','https://www.yelp.com/biz/los-tapatios-cedar-hill','https://www.yelp.com/biz/chengdu-46-clifton','https://www.yelp.com/biz/moby-dick-house-of-kabob-fairfax','https://www.yelp.com/biz/natures-food-patch-clearwater','https://www.yelp.com/biz/taco-del-mar-hillsboro-3','https://www.yelp.com/biz/ms-tootsies-rbl-philadelphia','https://www.yelp.com/biz/the-big-c-athletic-club-concord','https://www.yelp.com/biz/west-hanover-pizzeria-hanover','https://www.yelp.com/biz/georges-pastaria-houston','https://www.yelp.com/biz/encuentro-oakland-3','https://www.yelp.com/biz/smokys-bbq-eldersburg','https://www.yelp.com/biz/ruby-tuesday-san-antonio','https://www.yelp.com/biz/saladworks-philadelphia-4','https://www.yelp.com/biz/captain-pizza-middleton','https://www.yelp.com/biz/bob-evans-fredericksburg-3','https://www.yelp.com/biz/frittata-clawson','https://www.yelp.com/biz/the-sandwich-spot-palm-springs','https://www.yelp.com/biz/freds-mexican-cafe-san-diego-4','https://www.yelp.com/biz/geordies-steak-phoenix-2','https://www.yelp.com/biz/five-guys-wayne-5','https://www.yelp.com/biz/zen-sushi-la-crescenta-2','https://www.yelp.com/biz/the-summit-steakhouse-aurora-2','https://www.yelp.com/biz/miramar-bistro-highwood','https://www.yelp.com/biz/mick-o-sheas-baltimore','https://www.yelp.com/biz/dennys-houston-30','https://www.yelp.com/biz/carls-jr-henderson-5','https://www.yelp.com/biz/mexican-town-restaurant-detroit','https://www.yelp.com/biz/sushi-roku-las-vegas','https://www.yelp.com/biz/giant-pizza-king-san-diego','https://www.yelp.com/biz/quiznos-brooklyn-6','https://www.yelp.com/biz/taco-bell-glen-ellyn','https://www.yelp.com/biz/las-tortas-locas-marietta','https://www.yelp.com/biz/smith-and-wollensky-las-vegas-2','https://www.yelp.com/biz/happy-garden-chinese-brighton','https://www.yelp.com/biz/urban-foodie-feed-store-college-park','https://www.yelp.com/biz/the-wolf-oakland','https://www.yelp.com/biz/scuzzis-italian-restaurant-san-antonio-4','https://www.yelp.com/biz/better-gourmet-health-kitchen-staten-island','https://www.yelp.com/biz/the-restaurant-and-cafe-warren','https://www.yelp.com/biz/mcdonalds-houston-214','https://www.yelp.com/biz/pyeong-chang-tofu-house-oakland','https://www.yelp.com/biz/maria-rosa-pizzeria-and-family-restaurant-flemington','https://www.yelp.com/biz/legends-sports-bar-and-grill-roseville-2','https://www.yelp.com/biz/villa-reale-pizzeria-and-restaurant-pittsburgh','https://www.yelp.com/biz/the-terrace-cafe-venice','https://www.yelp.com/biz/the-oval-room-washington-2','https://www.yelp.com/biz/high-point-coal-center','https://www.yelp.com/biz/j-and-s-montebello','https://www.yelp.com/biz/cheers-restaurant-and-bar-fort-lauderdale']
def parse_page(url):
# url = "https://www.yelp.com/biz/frances-san-francisco"
headers = {'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.90 Safari/537.36'}
response = requests.get(url, headers=headers, verify=False).text
parser = html.fromstring(response)
raw_name = parser.xpath("//h1[contains(#class,'page-title')]//text()")
raw_claimed = parser.xpath("//span[contains(#class,'claim-status_icon--claimed')]/parent::div/text()")
raw_reviews = parser.xpath("//div[contains(#class,'biz-main-info')]//span[contains(#class,'review-count rating-qualifier')]//text()")
raw_category = parser.xpath('//div[contains(#class,"biz-page-header")]//span[#class="category-str-list"]//a/text()')
hours_table = parser.xpath("//table[contains(#class,'hours-table')]//tr")
details_table = parser.xpath("//div[#class='short-def-list']//dl")
raw_map_link = parser.xpath("//a[#class='biz-map-directions']/img/#src")
raw_phone = parser.xpath(".//span[#class='biz-phone']//text()")
raw_address = parser.xpath('//div[#class="mapbox-text"]//div[contains(#class,"map-box-address")]//text()')
raw_wbsite_link = parser.xpath("//span[contains(#class,'biz-website')]/a/#href")
raw_price_range = parser.xpath("//dd[contains(#class,'price-description')]//text()")
raw_health_rating = parser.xpath("//dd[contains(#class,'health-score-description')]//text()")
rating_histogram = parser.xpath("//table[contains(#class,'histogram')]//tr[contains(#class,'histogram_row')]")
raw_ratings = parser.xpath("//div[contains(#class,'biz-page-header')]//div[contains(#class,'rating')]/#title")
working_hours = []
for hours in hours_table:
raw_day = hours.xpath(".//th//text()")
raw_timing = hours.xpath("./td//text()")
day = ''.join(raw_day).strip()
timing = ''.join(raw_timing).strip()
working_hours.append({day:timing})
info = []
for details in details_table:
raw_description_key = details.xpath('.//dt//text()')
raw_description_value = details.xpath('.//dd//text()')
description_key = ''.join(raw_description_key).strip()
description_value = ''.join(raw_description_value).strip()
info.append({description_key:description_value})
ratings_histogram = []
for ratings in rating_histogram:
raw_rating_key = ratings.xpath(".//th//text()")
raw_rating_value = ratings.xpath(".//td[#class='histogram_count']//text()")
rating_key = ''.join(raw_rating_key).strip()
rating_value = ''.join(raw_rating_value).strip()
ratings_histogram.append({rating_key:rating_value})
name = ''.join(raw_name).strip()
phone = ''.join(raw_phone).strip()
address = ' '.join(' '.join(raw_address).split())
health_rating = ''.join(raw_health_rating).strip()
price_range = ''.join(raw_price_range).strip()
claimed_status = ''.join(raw_claimed).strip()
reviews = ''.join(raw_reviews).strip()
category = ','.join(raw_category)
cleaned_ratings = ''.join(raw_ratings).strip()
if raw_wbsite_link:
decoded_raw_website_link = urllib.unquote(raw_wbsite_link[0])
website = re.findall("biz_redir\?url=(.*)&website_link",decoded_raw_website_link)[0]
else:
website = ''
if raw_map_link:
decoded_map_url = urllib.unquote(raw_map_link[0])
map_coordinates = re.findall("center=([+-]?\d+.\d+,[+-]?\d+\.\d+)",decoded_map_url)[0].split(',')
latitude = map_coordinates[0]
longitude = map_coordinates[1]
else:
latitude = ''
longitude = ''
if raw_ratings:
ratings = re.findall("\d+[.,]?\d+",cleaned_ratings)[0]
else:
ratings = 0
data={'working_hours':working_hours,
'info':info,
'ratings_histogram':ratings_histogram,
'name':name,
'phone':phone,
'ratings':ratings,
'address':address,
'health_rating':health_rating,
'price_range':price_range,
'claimed_status':claimed_status,
'reviews':reviews,
'category':category,
'website':website,
'latitude':latitude,
'longitude':longitude,
'url':url,
}
return data
def parse_reviews(url):
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:47.0) Gecko/20100101 Firefox/47.0 Mozilla/5.0 (Macintosh; Intel Mac OS X x.y; rv:42.0) Gecko/20100101 Firefox/42.0.'}
response = requests.get(url, headers=headers, verify=False).text
parser = html.fromstring(response)
ratings_zipped = []
reviews = [x for x in parser.xpath("//div[contains(#class,'main-section')]//div[contains(#class,'review-list')]//div[contains(#class,'review')]//div[contains(#class,'review-content')]")]
for r in reviews:
date = r.xpath("./div[contains(#class,'biz-rating')]//span[contains(#class,'rating-qualifier')]/text()")[0].strip()
rating = r.xpath("./div[contains(#class,'biz-rating')]//div[contains(#class,'rating-large')]/#title")[0]
content = r.xpath("./p")[0].text_content()
ratings_zipped.append([date, rating, content])
print (len(ratings_zipped))
return ratings_zipped
def chunks(l, n):
"""Yield successive n-sized chunks from l."""
for i in range(0, len(l), n):
yield l[i:i + n]
def parse_pagination(url):
print (url)
headers = {'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.90 Safari/537.36'}
response = requests.get(url, headers=headers, verify=False)
print (response)
parser = html.fromstring(response.text)
try:
results = (int(parser.xpath("//div[contains(#class,'page-of-pages')]//text()")[0].strip().split(' ').pop()))*20
except IndexError:
results = 20
print (results)
return results
def get_businesses_data(data):
businesses, failed_searches = [], []
start_time = time.time()
result = {}
for i,url in enumerate(data):
print ('Starting iteration: ', i)
result['url']= url
pagination = parse_pagination(url)
print ('Pagination: ', pagination)
info = parse_page(url)
result['info'] = info
_reviews = []
for v in xrange(0,pagination,20):
paginated_url = result['url'].split('?')[0] + '?start='+str(v)
print ('Scraping Reviews: ', paginated_url)
_reviews += parse_reviews(paginated_url)
time.sleep(.5)
result['scraped_reviews'] = _reviews
result['scraped_reviews_count'] = len(_reviews)
businesses.append(result)
print ('Success iteration: ', i)
# print ('Results: ', result)
print ('Num of reviews: ', str(len(_reviews)))
print('')
print ('Time Elapsed: ', str(time.time() - start_time))
return businesses
if __name__=="__main__":
index = 5
#0
size = 20
i = index*20
chunk = yelp_urls[i:i+size]
businesses = get_businesses_data(chunk)
with open ('results/run_3/output_{}.json'.format(i), 'w') as f:
json.dump(businesses,f)
'''

from exceptions import ValueError
You don't need to do that at all, ValueError is part of the built-in exceptions, not to mention the fact that you never use it in your code

How can I download high resolution images from google use python + selenium + phantomJS

I want to fetch more than 100 high resolution images from google, use python2.7 + selenium + PhantomJS.
But since I act like they said, I could only get a webpage with small images on it. And I can't find out any link to the high resolution pictures directly. How could I fix it?
My code is as below.
from bs4 import BeautifulSoup
from selenium import webdriver
import time
class ImgCrawler:
def __init__(self,searchlink = None):
self.link = searchlink
self.soupheader = {'User-Agent':"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.2357.134 Safari/537.36"}
self.scrolldown = None
self.jsdriver = None
def getPhantomJSDriver(self):
self.jsdriver = webdriver.PhantomJS()
self.jsdriver.get(self.link)
def scrollDownUsePhatomJS(self, scrolltimes = 1, sleeptime = 10):
for i in range(scrolltimes):
self.jsdriver.execute_script('window.scrollTo(0,document.body.scrollHeight);')
time.sleep(sleeptime)
def getSoup(self, parser=None):
print 'a', self.jsdriver.page_source
return BeautifulSoup(self.jsdriver.page_source, parser)
def getActualUrl(self, soup=None, flag=None, classflag=None, jsonflaglink=None, jsonflagtype=None):
actualurl = []
for a in soup.find_all(flag, {"class": classflag}):
link = json.loads(a.text)[jsonflaglink]
filetype = json.loads(a.text)[jsonflagtype]
detailurl = link + u'.' + filetype
actualurl.append(detailurl)
return actualurl
if __name__ == '__main__':
search_url = "https://www.google.com.hk/search?safe=strict&hl=zh-CN&site=imghp&tbm=isch&source=hp&biw=&bih=&btnG=Google+%E6%90%9C%E7%B4%A2&q="
queryword = raw_input()
query = queryword.split()
query = '+'.join(query)
weblink = search_url + query
img = ImgCrawler(weblink)
img.getPhantomJSDriver()
img.scrollDownUsePhatomJS(2,5)
soup = img.getSoup('html.parser')
print weblink
print soup
actualurllist = img.getActualUrl(soup,'div','rg_meta','ou','ity')
print len(actualurllist)

I tried for a long time to use PhantomJS but ended up using Chrome which is not what you asked for I know, but it works. I could not get it to work with PhantomJS.
First get a driver https://sites.google.com/a/chromium.org/chromedriver/downloads you can use a headless version of chrome "Chrome Canary" if you are on Windows.
from bs4 import BeautifulSoup
from selenium import webdriver
import time
import re
import urlparse
class ImgCrawler:
def __init__(self,searchlink = None):
self.link = searchlink
self.soupheader = {'User-Agent':"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.2357.134 Safari/537.36"}
self.scrolldown = None
self.jsdriver = None
def getPhantomJSDriver(self):
self.jsdriver = webdriver.Chrome()
self.jsdriver.get(self.link)
def scrollDownUsePhatomJS(self, scrolltimes = 1, sleeptime = 10):
for i in range(scrolltimes):
self.jsdriver.execute_script('window.scrollTo(0,document.body.scrollHeight);')
time.sleep(sleeptime)
def getSoup(self, parser=None):
print 'a', self.jsdriver.page_source
return BeautifulSoup(self.jsdriver.page_source, parser)
def getActualUrl(self, soup=None):
actualurl = []
r = re.compile(r"/imgres\?imgurl=")
for a in soup.find_all('a', href=r):
parsed = urlparse.urlparse(a['href'])
url = urlparse.parse_qs(parsed.query)['imgurl']
actualurl.append(url)
print url
return actualurl
if __name__ == '__main__':
search_url = "https://www.google.com.hk/search?safe=strict&hl=zh-CN&site=imghp&tbm=isch&source=hp&biw=&bih=&btnG=Google+%E6%90%9C%E7%B4%A2&q="
queryword = raw_input()
query = queryword.split()
query = '+'.join(query)
weblink = search_url + query
img = ImgCrawler(weblink)
img.getPhantomJSDriver()
img.scrollDownUsePhatomJS(2,5)
soup = img.getSoup('html.parser')
print weblink
print soup
actualurllist = img.getActualUrl(soup)
print len(actualurllist)
I changed getActualUrl() to get the image url from an "a" element with a "href" attribute starting with "/imgres?imgurl="
Outputs (when "hazard" is typed in to the terminal):
[u'https://static.independent.co.uk/s3fs-public/styles/article_small/public/thumbnails/image/2016/12/26/16/eden-hazard.jpg']
[u'https://upload.wikimedia.org/wikipedia/commons/thumb/b/b1/EdenHazardDecember_2016.jpg/200px-EdenHazardDecember_2016.jpg']
[u'http://a.espncdn.com/combiner/i/?img=/photo/2016/1227/r166293_1296x729_16-9.jpg&w=738&site=espnfc']
[u'https://platform-static-files.s3.amazonaws.com/premierleague/photos/players/250x250/p42786.png']
[u'https://upload.wikimedia.org/wikipedia/commons/thumb/7/74/Eden_Hazard_-_DK-Chel15_%286%29.jpg/150px-Eden_Hazard_-_DK-Chel15_%286%29.jpg']
[u'http://a.espncdn.com/combiner/i/?img=/photo/2017/0117/r172004_1296x729_16-9.jpg&w=738&site=espnfc']
[u'http://images.performgroup.com/di/library/GOAL/98/c0/eden-hazard-chelsea_1eohde060wvft1elcskrgihxq3.jpg?t=-1500575837&w=620&h=430']
[u'http://e1.365dm.com/17/03/16-9/20/skysports-eden-hazard-chelsea_3918835.jpg?20170331154242']
[u'http://a.espncdn.com/combiner/i/?img=/photo/2017/0402/r196036_1296x729_16-9.jpg&w=738&site=espnfc']
[u'https://www.thesun.co.uk/wp-content/uploads/2017/04/nintchdbpict000316361045.jpg?strip=all&w=670&quality=100']
[u'https://static.independent.co.uk/s3fs-public/thumbnails/image/2017/02/10/14/eden-hazard1.jpg']
[u'http://s.newsweek.com/sites/www.newsweek.com/files/2016/11/07/eden-hazard.jpg']
[u'http://www.newstube24.com/wp-content/uploads/2017/06/haz.jpg']
[u'http://images.performgroup.com/di/library/GOAL/17/b1/eden-hazard_68ypnelg3lfd14oxkffztftt6.png?t=-1802977526&w=620&h=430']
[u'https://upload.wikimedia.org/wikipedia/commons/thumb/e/eb/DK-Chel15_%288%29.jpg/220px-DK-Chel15_%288%29.jpg']
[u'http://images.performgroup.com/di/library/omnisport/50/3f/hazard-cropped_3y08vc3ejpua168e9mgvu4mwc.jpg?t=-930203025&w=620&h=430']
[u'https://www.thesun.co.uk/wp-content/uploads/2017/03/nintchdbpict000291621611-e1490777105213.jpg?strip=all&w=745&quality=100']
[u'https://static.independent.co.uk/s3fs-public/thumbnails/image/2016/01/14/14/Eden-Hazard.jpg']
[u'https://upload.wikimedia.org/wikipedia/commons/thumb/5/56/Eden_Hazard%2713-14.JPG/150px-Eden_Hazard%2713-14.JPG']
[u'https://www.thesun.co.uk/wp-content/uploads/2017/03/nintchdbpict000296311943-e1490777241155.jpg?strip=all&w=596&quality=100']
[u'https://static.independent.co.uk/s3fs-public/thumbnails/image/2016/01/27/11/hazard.jpg']
[u'http://www.newzimbabwe.com/FCKEditor_Images/Eden-Hazard-896286.jpg']
[u'http://images.performgroup.com/di/library/GOAL/9c/93/eden-hazard_d4lbib7wdagw1hp2e5gnyov0k.jpg?t=-1763574189&w=620&h=430']
[u'http://www.guoguiyan.com/data/out/94/69914569-hazard-wallpapers.jpg']
[u'http://static.guim.co.uk/sys-images/Football/Pix/pictures/2015/4/16/1429206099512/Eden-Hazard-009.jpg']
[u'https://metrouk2.files.wordpress.com/2017/04/pri_37621532.jpg?w=620&h=406&crop=1']
[u'http://alummata.com/wp-content/uploads/2016/04/Hazard.jpg']
[u'https://upload.wikimedia.org/wikipedia/commons/thumb/d/d3/Hazard_vs_Norwich_%28crop%29.jpg/150px-Hazard_vs_Norwich_%28crop%29.jpg']
[u'http://i.dailymail.co.uk/i/pix/2016/11/06/20/3A185FB800000578-3910886-image-a-46_1478462522592.jpg']
[u'http://cdn.images.express.co.uk/img/dynamic/67/590x/467822629-465742.jpg']
[u'http://i.dailymail.co.uk/i/pix/2015/10/17/18/2D81CB1D00000578-0-image-a-37_1445102645249.jpg']
[u'http://images.performgroup.com/di/library/GOAL_INTERNATIONAL/27/ce/eden-hazard_1kepw6rvweted1hpfmp5xwd5cs.jpg?t=-228379025&w=620&h=430']
[u'http://img.skysports.com/16/12/768x432/skysports-chelsea-manchester-city-eden-hazard_3845204.jpg?20161203162258']
[u'https://www.thesun.co.uk/wp-content/uploads/2017/03/nintchdbpict0003089026162.jpg?strip=all&w=960&quality=100']
[u'http://www.chelseafc.com/content/cfc/en/homepage/news/boilerplate-config/latest-news/2016/05/hazard--rediscovering-our-form.img.png']
[u'http://images.performgroup.com/di/library/omnisport/b5/98/hazard-cropped_172u0n8wx4j071cvgs1n3yycvw.jpg?t=2030908123&w=620&h=430']
[u'http://images.indianexpress.com/2016/05/eden-hazard-m.jpg']
[u'http://i2.mirror.co.uk/incoming/article9755579.ece/ALTERNATES/s615/PAY-Chelsea-v-Arsenal-Premier-League.jpg']
[u'http://www.chelseafc.com/content/cfc/en/homepage/news/boilerplate-config/latest-news/2017/06/hazard-injury-update.img.png']
[u'http://futhead.cursecdn.com/static/img/fm/17/players/183277_HAZARDCAM7.png']
[u'http://images.performgroup.com/di/library/GOAL/4d/6/eden-hazard-chelsea-06032017_enh1ll3uadj01ocstyopie9e4.jpg?t=-1521106510&w=620&h=430']
[u'http://images.performgroup.com/di/library/GOAL/34/8/eden-hazard-chelsea-southampton_1oca1rpy37gmn1ldmqvytti3k4.jpg?t=-1501721805&w=620&h=430']
[u'http://media.gettyimages.com/photos/eden-hazard-of-chelsea-celebrates-scoring-his-sides-third-goal-during-picture-id617452212?s=612x612']
[u'http://cdn.images.express.co.uk/img/dynamic/67/590x/secondary/Eden-Hazard-889782.jpg']
[u'https://static.independent.co.uk/s3fs-public/thumbnails/image/2015/10/19/16/Hazard.jpg']
[u'https://www.thesun.co.uk/wp-content/uploads/2017/03/nintchdbpict000307050894.jpg?strip=all&w=660&quality=100']
[u'http://e1.365dm.com/16/11/16-9/20/skysports-eden-hazard-chelsea-football_3833122.jpg?20161116153005']
[u'http://thumb.besoccer.com/media/img_news/morata-y-hazard--besoccer.jpg']
[u'https://static.independent.co.uk/s3fs-public/styles/story_medium/public/thumbnails/image/2017/03/13/21/10-hazard.jpg']
[u'https://static.independent.co.uk/s3fs-public/styles/story_medium/public/thumbnails/image/2016/12/27/13/hazard.jpg']
[u'http://images.performgroup.com/di/library/GOAL/63/2a/eden-hazard-chelsea_15ggj1j39rmky1c5a20oxt3tly.jpg?t=1297762370']
[u'http://i1.mirror.co.uk/incoming/article9755531.ece/ALTERNATES/s615b/Chelsea-v-Arsenal-Premier-League.jpg']
[u'http://cf.c.ooyala.com/l2YmpyYjE6yvLSxGiEebNMr3N1ANS1Xc/O0cEsGv5RdudyPNn4xMDoxOjBnO_4SLA']
[u'http://media.gettyimages.com/photos/eden-hazard-of-chelsea-celebrates-scoring-his-sides-third-goal-during-picture-id617452006?s=612x612']
[u'http://a.espncdn.com/combiner/i/?img=/photo/2017/0413/r199412_2_1296x729_16-9.jpg&w=738&site=espnfc']
[u'https://www.thesun.co.uk/wp-content/uploads/2017/04/nintchdbpict000318703991-e1493109803795.jpg?strip=all&w=960&quality=100']
[u'https://static.independent.co.uk/s3fs-public/styles/story_medium/public/thumbnails/image/2016/11/18/14/hazard-award.jpg']
[u'http://static.goal.com/2477200/2477282_heroa.jpg']
[u'https://static.independent.co.uk/s3fs-public/thumbnails/image/2016/12/16/14/eden-hazard.jpg']
[u'http://www.guoguiyan.com/data/out/94/69979129-hazard-wallpapers.jpg']
[u'https://www.thesun.co.uk/wp-content/uploads/2016/11/nintchdbpict0002769424741.jpg?w=960&strip=all']
[u'http://v.uecdn.es/p/110/thumbnail/entry_id/0_ofavjqr8/width/660/cache_st/20170327164629/type/2/bgcolor/000000/0_ofavjqr8.jpg']
[u'https://static.independent.co.uk/s3fs-public/thumbnails/image/2017/02/07/10/edenhazard.jpg']
[u'http://theworldgame.sbs.com.au/sites/sbs.com.au.theworldgame/files/styles/full/public/images/e/d/eden-hazard-cropped_g6m28ldoc0b41p3f5sp2vlflt.jpg?itok=XW5M7QEA']
[u'http://e0.365dm.com/17/03/16-9/20/skysports-eden-hazard-chelsea_3909051.jpg?20170314181126']
[u'http://cdn.images.express.co.uk/img/dynamic/67/590x/secondary/Chelsea-Hazard-goals-886084.jpg']
[u'https://www.thesun.co.uk/wp-content/uploads/2017/04/nintchdbpict000319343894.jpg?strip=all&w=960&quality=100']
[u'https://www.footyrenders.com/render/Eden-Hazard-PL.png']
[u'http://media.gettyimages.com/photos/eden-hazard-of-chelsea-celebrates-as-he-scores-their-first-goal-the-picture-id672946758?s=612x612']
[u'https://pbs.twimg.com/profile_images/791664465729163264/XbCVl6BF.jpg']
[u'https://upload.wikimedia.org/wikipedia/commons/thumb/9/95/Eden_Hazard_2011.jpg/170px-Eden_Hazard_2011.jpg']
[u'http://s.newsweek.com/sites/www.newsweek.com/files/2016/02/01/guus-hiddink-says-eden-hazard-could-leave-chelsea..jpg']
[u'https://www.thesun.co.uk/wp-content/uploads/2016/06/chelsea_hazard_mobile_top.jpg?strip=all&w=750&h=352&crop=1']
[u'http://cdn.images.dailystar.co.uk/dynamic/58/photos/735000/Eden-Hazard-887735.jpg']
[u'http://i.telegraph.co.uk/multimedia/archive/03580/Hazard_Real_copy_3580583b.jpg']
[u'https://premierleague-static-files.s3.amazonaws.com/premierleague/photo/2017/05/21/47a1f452-43e4-4215-a5b8-5043c1e12a07/686302908.jpg']
[u'http://www.chelseafc.com/content/cfc/en/homepage/news/boilerplate-config/latest-news/2017/06/hazard-s-highlights.img.png']
[u'http://i.dailymail.co.uk/i/pix/2016/12/14/15/3B45B4D300000578-4032306-Hazard_PFA_Player_of_the_Year_in_2015_has_rediscovered_his_form_-a-6_1481728291902.jpg']
[u'https://img.rasset.ie/000d5137-800.jpg']
[u'http://cdn.images.express.co.uk/img/dynamic/67/590x/Eden-Hazard-665260.jpg']
[u'http://cdn.images.express.co.uk/img/dynamic/67/590x/Eden-Hazard-659164.jpg']
[u'http://cdn.images.express.co.uk/img/dynamic/67/590x/secondary/Hazard-scored-Chelsea-s-third-goal-against-Tottenham-909804.jpg']
[u'http://cdn.images.dailystar.co.uk/dynamic/58/photos/237000/Eden-Hazard-887237.jpg']
[u'http://a.espncdn.com/combiner/i/?img=/media/motion/ESPNi/2017/0405/int_170405_Hazard_the_successor_to_Ronaldo_at_Real/int_170405_Hazard_the_successor_to_Ronaldo_at_Real.jpg&w=738&site=espnfc']
[u'http://cdn.images.express.co.uk/img/dynamic/67/590x/Eden-Hazard-721522.jpg']
[u'http://media.gettyimages.com/photos/eden-hazard-of-chelsea-celebrates-with-teammates-after-scoring-his-picture-id633776492?s=612x612']
[u'http://betinmalta.com/wp-content/uploads/2017/05/hazard.jpg']
[u'http://cdn.images.dailystar.co.uk/dynamic/58/photos/708000/Eden-Hazard-Chelsea-712708.jpg']
[u'http://images.performgroup.com/di/library/omnisport/c9/4a/eden-hazard-cropped_12u5irb6bkze1cue2wpjzxa44.jpg?t=-2084914038&w=620&h=430']
[u'https://www.thesun.co.uk/wp-content/uploads/2017/06/nintchdbpict0003291256741.jpg?strip=all&w=714&quality=100']
[u'https://premierleague-static-files.s3.amazonaws.com/premierleague/photo/2017/03/10/f97d36aa-1eef-4a78-996f-63d543c79efc/700017169TS004_Eden_Hazard_.JPG']
[u'https://s-media-cache-ak0.pinimg.com/736x/f0/01/17/f001178defb2b3be3cffb5e9b792748b--eden-hazard-liverpool-england.jpg']
[u'http://i4.mirror.co.uk/incoming/article9898829.ece/ALTERNATES/s615b/hazard-2.jpg']
[u'http://images.performgroup.com/di/library/GOAL/24/76/eden-hazard-and-lionel-messi_kamv8simc20x1p2i2fcf7lllw.png?t=421166242&w=620&h=430']
[u'https://metrouk2.files.wordpress.com/2017/03/gettyimages-618471206.jpg?w=748&h=498&crop=1']
[u'http://cdn.images.express.co.uk/img/dynamic/67/590x/Hazard-Chelsea-658138.jpg']
[u'https://static.independent.co.uk/s3fs-public/thumbnails/image/2017/04/23/17/hazard.jpg']
[u'http://e0.365dm.com/15/10/16-9/20/eden-hazard-comparison-chelsea_3365521.jpg?20151018152317']
[u'http://cdn.images.express.co.uk/img/dynamic/galleries/x701/231048.jpg']
[u'http://cdn.images.express.co.uk/img/dynamic/galleries/x701/102742.jpg']
[u'https://i.ytimg.com/vi/GWhVkFTe_BY/maxresdefault.jpg']
[u'https://www.thesun.co.uk/wp-content/uploads/2017/05/nintchdbpict000319343748-e1496260888520.jpg?strip=all&w=960&quality=100']
[u'https://metrouk2.files.wordpress.com/2017/06/689818982.jpg?w=748&h=498&crop=1']
[u'https://www.thesun.co.uk/wp-content/uploads/2017/03/nintchdbpict000308902470.jpg?strip=all&w=960&quality=100']
[u'https://www.thesun.co.uk/wp-content/uploads/2016/12/nintchdbpict000289569836.jpg?w=960&strip=all']
[u'https://i.ytimg.com/vi/zZ9stt70_vU/maxresdefault.jpg']
[u'https://upload.wikimedia.org/wikipedia/commons/2/2c/Kylian_Hazard_%28cropped%29.jpg']
[u'http://e00-marca.uecdn.es/assets/multimedia/imagenes/2017/03/26/14905092504845.jpg']
[u'http://images.performgroup.com/di/library/omnisport/ba/47/eden-hazard-cropped_rccnpv1me3v51kqpnj5ak4nko.jpg?t=1222186324&w=620&h=430']
[u'http://cdn.images.express.co.uk/img/dynamic/67/590x/secondary/Eden-Hazard-922505.jpg']
[u'https://s-media-cache-ak0.pinimg.com/736x/48/ce/4c/48ce4c478d8b06dccacce352d9d4bdc2--eden-hazard-pogba.jpg']
[u'http://www.telegraph.co.uk/content/dam/football/2016/10/23/111897755_Editorial_use_only_No_merchandising_For_Football_images_FA_and_Premier_League_restrict-large_trans_NvBQzQNjv4BqqVzuuqpFlyLIwiB6NTmJwfSVWeZ_vEN7c6bHu2jJnT8.jpg']
[u'https://metrouk2.files.wordpress.com/2017/06/686902184.jpg?w=748&h=652&crop=1']
[u'https://www.thesun.co.uk/wp-content/uploads/2017/03/nintchdbpict0003086723271-e1489501904590.jpg?strip=all&w=960&quality=100']
[u'http://e2.365dm.com/17/01/16-9/20/skysports-chelsea-manchester-city-eden-hazard_3862340.jpg?20170406190414']
[u'http://www.telegraph.co.uk/content/dam/football/2017/05/26/TELEMMGLPICT000129483487-large_trans_NvBQzQNjv4BqajCpFXsei0OXjDFGPZkcdJOkVdu-K0ystYH4SV7DHn8.jpeg']
[u'https://i.ytimg.com/vi/FFE4Ea437ks/maxresdefault.jpg']
[u'https://i1.wp.com/www.vanguardngr.com/wp-content/uploads/2017/03/Hazard-madrid.png?resize=350%2C200']
[u'http://china.chelseafc.com/content/cfc/zh/homepage/teams/first-team/eden-hazard/summary/_jcr_content/tabparmain/box/box/textimage/image.img.jpg/1496846329140.jpg']
[u'http://static.goal.com/198700/198707_news.jpg']
[u'https://www.thesun.co.uk/wp-content/uploads/2017/05/nintchdbpict000319357531.jpg?strip=all&w=960&quality=100']
[u'http://media.gettyimages.com/photos/eden-hazard-of-chelsea-poses-with-the-premier-league-trophy-after-the-picture-id686826640?s=612x612']
[u'http://cf.c.ooyala.com/t3dXdzYjE6VJktcnKdi7F2205I_mSSKQ/eWNh-8akTAF2kj8X4xMDoxOjBnO_4SLA']
[u'http://c.smimg.net/16/39/300x225/eden-hazard.jpg']
[u'http://www.whatfootballersearn.com/wp-content/uploads/Eden-Hazard.jpg']
[u'http://cdn.images.dailystar.co.uk/dynamic/58/photos/328000/Eden-Hazard-437328.jpg']
[u'http://cdn.images.express.co.uk/img/dynamic/67/590x/secondary/Eden-Hazard-Chelsea-882846.jpg']
[u'http://cdn.images.express.co.uk/img/dynamic/67/590x/Chelsea-star-Eden-Hazard-741161.jpg']
[u'https://talksport.com/sites/default/files/styles/taxonomy-img/public/field/image/201703/hazard_0.jpg']
[u'http://i.dailymail.co.uk/i/pix/2016/08/28/21/37A101A700000578-3762573-image-a-19_1472417354943.jpg']
[u'http://www.telegraph.co.uk/content/dam/football/2016/07/27/87650659-edenhazard-sport-large_trans_NvBQzQNjv4BqqVzuuqpFlyLIwiB6NTmJwfSVWeZ_vEN7c6bHu2jJnT8.jpg']
[u'http://cdn.images.dailystar.co.uk/dynamic/58/photos/165000/620x/Eden-Hazard-598896.jpg']
[u'http://i.dailymail.co.uk/i/pix/2016/05/04/21/33C8A26600000578-0-image-a-19_1462392130112.jpg']
[u'https://ichef-1.bbci.co.uk/news/660/cpsprodpb/13AA1/production/_96354508_595836d4-f21a-419b-95cb-37a65204f6eb.jpg']
[u'https://premierleague-static-files.s3.amazonaws.com/premierleague/photo/2016/11/30/1eb421ae-b210-4a01-95bb-36f509826cc1/Debruyne_v_Hazard.jpg']
[u'https://www.thesun.co.uk/wp-content/uploads/2017/03/nintchdbpict000309639487-e1490040388851.jpg?strip=all&w=739&quality=100']
[u'http://static.goal.com/3311200/3311292_heroa.jpg']
[u'http://i3.mirror.co.uk/incoming/article7986781.ece/ALTERNATES/s615b/Hazard-and-son.jpg']
[u'http://a.espncdn.com/combiner/i/?img=/photo/2016/0916/r126535_1296x729_16-9.jpg&w=738&site=espnfc']
[u'http://www.chelseafc.com/content/cfc/en/homepage/news/boilerplate-config/latest-news/2017/03/hazard-score-is-number-one-.img.png']
[u'https://static.independent.co.uk/s3fs-public/thumbnails/image/2015/03/17/13/eden-hazard.jpg']
[u'https://metrouk2.files.wordpress.com/2017/05/680506564.jpg?w=748&h=457&crop=1']
[u'http://media.gettyimages.com/photos/eden-hazard-of-chelsea-celebrates-with-diego-costa-of-chelsea-after-picture-id671559962?s=612x612']
[u'http://e0.365dm.com/17/05/16-9/20/skysports-eden-hazard-chelsea_3965489.jpg?20170529101357']
[u'https://s-media-cache-ak0.pinimg.com/736x/e0/80/0e/e0800e380ef363594fb292969b7c5b64--eden-hazard-chelsea-soccer.jpg']
[u'http://cdn-football365.365.co.za/content/uploads/2016/12/GettyImages.630542828.jpg']
[u'http://i.dailymail.co.uk/i/pix/2016/07/16/19/340E4A9A00000578-3693637-image-a-84_1468694248523.jpg']
[u'http://www.squawka.com/news/wp-content/uploads/2017/01/hazard-chelsea-e1485528066609.jpg']
[u'http://www.guoguiyan.com/data/out/94/68880901-hazard-wallpapers.jpg']
[u'http://www.telegraph.co.uk/content/dam/football/2017/03/12/JS122962983_EHazDavid-Rose-large_trans_NvBQzQNjv4BqtA9hvt4yaDuJhaJG2frTIUNrh1MdssoHpGF6OIxC49c.jpg']
[u'http://images.performgroup.com/di/library/GOAL/17/25/eden-hazard-chelsea_1dsnlf2z113cx10nxvp9ydudcz.jpg?t=2008335075']
[u'http://www.telegraph.co.uk/content/dam/football/2016/12/05/115182685-eden-hazard-sport-large_trans_NvBQzQNjv4BqA7a2BP2KFPtZUOepzpZgXISdNn8DgVUcalGVREaviFE.jpg']
[u'https://www.thesun.co.uk/wp-content/uploads/2017/04/sport-preview-morata-hazard.jpg?strip=all&quality=100&w=750&h=500&crop=1']
[u'http://thumb.besoccer.com/media/img_news/eden-hazard--futbolista-del-chelsea--chelseafc.jpg']
[u'http://i4.mirror.co.uk/incoming/article7374471.ece/ALTERNATES/s615/Chelsea-Training-Session.jpg']
[u'https://metrouk2.files.wordpress.com/2017/04/671549404.jpg?w=748&h=532&crop=1']
[u'https://metrouk2.files.wordpress.com/2016/02/462363538.jpg?w=748&h=563&crop=1']
[u'https://metrouk2.files.wordpress.com/2017/05/6834221661.jpg?w=748&h=507&crop=1']
[u'http://cdn.images.express.co.uk/img/dynamic/67/590x/Chelsea-star-Eden-Hazard-739447.jpg']
[u'http://cdn.quotesgram.com/img/21/41/114220036-24CA6E4700000578-2916442-Eden_Hazard_has_been_instrumental_for_Chelsea_this_season_as_the-a-7_1421682779132.jpg']
[u'http://i.dailymail.co.uk/i/pix/2016/09/29/09/38E4401500000578-3813294-image-a-1_1475138637248.jpg']
[u'http://healthyceleb.com/wp-content/uploads/2016/04/Eden-Hazard-match-between-Chelsea-Milton-Keynes-Dons-January-2016.jpg']
[u'https://talksport.com/sites/default/files/styles/taxonomy-img/public/field/image/201704/gettyimages-663029916.jpg']
[u'https://upload.wikimedia.org/wikipedia/commons/thumb/2/29/Thorgan_Hazard_2014.jpg/220px-Thorgan_Hazard_2014.jpg']
[u'http://cdn.images.dailystar.co.uk/dynamic/58/photos/91000/620x/Eden-Hazard-632850.jpg']
[u'http://i4.mirror.co.uk/incoming/article7531141.ece/ALTERNATES/s615/A-dejected-looking-Eden-Hazard.jpg']
[u'https://www.thesun.co.uk/wp-content/uploads/2017/05/nintchdbpict000322464448-e1494602676644.jpg?strip=all&w=960&quality=100']
[u'http://images.performgroup.com/di/library/GOAL_INTERNATIONAL/76/92/chelsea-bournemouth-eden-hazard_148j4p900kzba159diso6ewwvo.jpg?t=1004329665&w=620&h=430']
[u'https://images.cdn.fourfourtwo.com/sites/fourfourtwo.com/files/styles/inline-image/public/hazard3.jpg?itok=ap0DtuZx']
[u'https://talksport.com/sites/default/files/styles/taxonomy-img/public/field/image/201707/hazard.jpg']
...
[u'http://a.espncdn.com/combiner/i/?img=/photo/2017/0330/r195127_1296x729_16-9.jpg&w=738&site=espnfc']
299

Python + lxml + etree Encoding issue

I'm trying to parse some pages by using this code:
import urllib.request
import requests
from lxml import etree
s = requests.session()
s.headers.update({
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.9; rv:45.0)
Gecko/20100101 Firefox/45.0'
})
results = open("res.txt", "w")
for i in range(510077, 2780673):
results = open("res.txt", "a")
print(i)
url = "url" + str(i) + "&print=true"
try:
content = s.get(url).text
tree = etree.HTML(content)
a = str(tree.xpath("//*[#class='prob_nums']")[0].text)
b = etree.tostring(tree.xpath("//*[#class='pbody']")[0])
c = etree.tostring(tree.xpath("//*[#class='nobreak solution']")[0])
results.writelines("%s %s %s" % (a, b, c))
results.close()
except Exception:
print("error")
But have a problem with output:
(fragment)
<p class="left_margin">На доске на­пи­са
How to convert these symbols to normal text? Thank you

Categories

Resources