Please Help me
I have a data url in the CSV file, in that file there are 100 rows and 1 column,
I want to load data line 1 to line 100 from CSV using Python, how do I write the code line?
However, after running the repetition can only work once in one of the lines does not reach the end of the url in the CSV and does not continue to the next URL.
disc_information = html.find('div', class_='alert alert-info global-promo').text.strip().strip('\n')
AttributeError: 'NoneType' object has no attribute 'text'
how do I get through if an error occurs when html is not found?
the following line of code I use python, please help so that the looping scrape runs to the end of the url list
from bs4 import BeautifulSoup
import requests
import pandas as pd
import csv
import pandas
with open('Url Torch.csv','rt') as f:
data = csv.reader(f, delimiter=',')
for row in data:
URL_GO = row[2]
def variable_Scrape(url):
try:
cookies = dict(cookie="............")
request = requests.get(url, cookies=cookies)
html = BeautifulSoup(request.content, 'html.parser')
title = html.find('div', class_='title').text.strip().strip('\n')
desc = html.find('div', class_='content').text
link = html.find_all('img', class_='lazyload slide-item owl-lazy')
normal_price = html.find('div', class_='amount public').text.strip().strip('\n')
disc_information = html.find('div', class_='alert alert-info global-promo').text.strip().strip('\n')
except AttributeError as e:
print(e)
#ConnectionAbortedError
return False
else:
print(title)
#print(desc)
#print(link)
finally:
print(title)
print(desc)
print(link)
print('Finally.....')
variable_Scrape(URL_GO)
Is hard to give you the exact answer without seeing you csv file but try this:
import csv
f = open('you_file.csv')
csv_f = csv.reader(f)
for row in csv_f:
print row[0]
This is the code
import csv
data = [] #create an empty list to store rows on it
with open('emails.csv') as csv_file:
reader = csv.reader(csv_file)
for row in reader:
data.append(row) #add each row to the list
Based on your comments about passing a loop when the url is not ok:
for url in data: # data is the list where url stored
try:
# do your code here (requests, beautifulsoup) :
# r = requests.get(url) ...
except:
pass
# will go to the next loop (next url) if an error happens
I'm trying to figure out what will be the next step to convert my webscrape to CSV.
I've tried putting every column into individual lists, but I feel like this is not the solution.
from bs4 import BeautifulSoup
import requests
url = 'https://www.pro-football-reference.com/years/2018/passing.htm'
page = requests.get(url)
soup = BeautifulSoup(page.content, 'html.parser')
for row in tb.find_all('tr'):
i = row.get_text()
print(i)
This should work
import csv #quite crucial
final_table = []
for row in tb.findall('tr'):
next_line = row.get_text()
final_table.append([next_line])
with open('output.csv', 'w') as f:
writer = csv.writer(f)
writer.writerows(final_table)
Use the csv module. We'll grab the headers with soup.find("tr").find_all("th"), then loop over the body and write it to the text file. The first cell of each row is a <th>, so we need to handle that separately and prepend it to the <td> data. Note that the staggered headers every 30 lines are omitted.
import csv
import requests
from bs4 import BeautifulSoup
url = "https://www.pro-football-reference.com/years/2018/passing.htm"
soup = BeautifulSoup(requests.get(url).content, "html.parser")
with open("output.csv", "w") as f:
writer = csv.writer(f)
writer.writerow([x.get_text() for x in soup.find("tr").find_all("th")])
for row in soup.find_all("tr"):
data = [row.find("th").get_text()] + [x.get_text() for x in row.find_all("td")]
if data:
writer.writerow(data)
Output (just the top few rows):
Rk,Player,Tm,Age,Pos,G,GS,QBrec,Cmp,Att,Cmp%,Yds,TD,TD%,Int,Int%,Lng,Y/A,AY/A,Y/C,Y/G,Rate,QBR,Sk,Yds,NY/A,ANY/A,Sk%,4QC,GWD
1,Ben Roethlisberger,PIT,36,QB,16,16,9-6-1,452,675,67.0,5129,34,5.0,16,2.4,97,7.6,7.5,11.3,320.6,96.5,71.0,24,166,7.10,7.04,3.4,2,3
2,Andrew Luck*,IND,29,QB,16,16,10-6-0,430,639,67.3,4593,39,6.1,15,2.3,68,7.2,7.4,10.7,287.1,98.7,69.4,18,134,6.79,6.95,2.7,3,3
3,Matt Ryan,ATL,33,QB,16,16,7-9-0,422,608,69.4,4924,35,5.8,7,1.2,75,8.1,8.7,11.7,307.8,108.1,68.5,42,296,7.12,7.71,6.5,1,1
4,Kirk Cousins,MIN,30,QB,16,16,8-7-1,425,606,70.1,4298,30,5.0,10,1.7,75,7.1,7.3,10.1,268.6,99.7,58.2,40,262,6.25,6.48,6.2,1,0
Check this thread if you see extra newlines in the CSV result on Windows.
I am crawling data from Wikipedia and it works so far. I can display it on the terminal, but I can't write it the way I need it into a csv file :-/
The code is pretty long, but I paste it here anyway and hope that somebody can help me.
import csv
import requests
from bs4 import BeautifulSoup
def spider():
url = 'https://de.wikipedia.org/wiki/Liste_der_Gro%C3%9F-_und_Mittelst%C3%A4dte_in_Deutschland'
code = requests.get(url).text # Read source code and make unicode
soup = BeautifulSoup(code, "lxml") # create BS object
table = soup.find(text="Rang").find_parent("table")
for row in table.find_all("tr")[1:]:
partial_url = row.find_all('a')[0].attrs['href']
full_url = "https://de.wikipedia.org" + partial_url
get_single_item_data(full_url) # goes into the individual sites
def get_single_item_data(item_url):
page = requests.get(item_url).text # Read source code & format with .text to unicode
soup = BeautifulSoup(page, "lxml") # create BS object
def getInfoBoxBasisDaten(s):
return str(s) == 'Basisdaten' and s.parent.name == 'th'
basisdaten = soup.find_all(string=getInfoBoxBasisDaten)[0]
basisdaten_list = ['Bundesland', 'Regierungsbezirk:', 'Höhe:', 'Fläche:', 'Einwohner:', 'Bevölkerungsdichte:',
'Postleitzahl', 'Vorwahl:', 'Kfz-Kennzeichen:', 'Gemeindeschlüssel:', 'Stadtgliederung:',
'Adresse', 'Anschrift', 'Webpräsenz:', 'Website:', 'Bürgermeister', 'Bürgermeisterin',
'Oberbürgermeister', 'Oberbürgermeisterin']
with open('staedte.csv', 'w', newline='', encoding='utf-8') as csvfile:
fieldnames = ['Bundesland', 'Regierungsbezirk:', 'Höhe:', 'Fläche:', 'Einwohner:', 'Bevölkerungsdichte:',
'Postleitzahl', 'Vorwahl:', 'Kfz-Kennzeichen:', 'Gemeindeschlüssel:', 'Stadtgliederung:',
'Adresse', 'Anschrift', 'Webpräsenz:', 'Website:', 'Bürgermeister', 'Bürgermeisterin',
'Oberbürgermeister', 'Oberbürgermeisterin']
writer = csv.DictWriter(csvfile, fieldnames=fieldnames, delimiter=';', quotechar='|', quoting=csv.QUOTE_MINIMAL, extrasaction='ignore')
writer.writeheader()
for i in basisdaten_list:
wanted = i
current = basisdaten.parent.parent.nextSibling
while True:
if not current.name:
current = current.nextSibling
continue
if wanted in current.text:
items = current.findAll('td')
print(BeautifulSoup.get_text(items[0]))
print(BeautifulSoup.get_text(items[1]))
writer.writerow({i: BeautifulSoup.get_text(items[1])})
if '<th ' in str(current): break
current = current.nextSibling
print(spider())
The output is incorrect in 2 ways. The cells are their right places and only one city is written, all others are missing. It looks like this:
But it should look like this + all other cities in it:
'... only one city is written ...': You call get_single_item_data for each city. Then inside this function you open the output file with the same name, in the statement with open('staedte.csv', 'w', newline='', encoding='utf-8') as csvfile: which will overwrite the output file each time you call the function.
Each variable is written to a new row: In the statement writer.writerow({i: BeautifulSoup.get_text(items[1])}) you write the value for one variable to a row. What you need to do instead is to make a dictionary for values before you start looking for page values. As you accumulate the values from the page you shove them into the dictionary by field name. Then after you have found all of the values available you call writer.writerow.
I'd like to get some quick help on writing this webscraping program. So far it's scraping things correctly, but I'm having trouble writing it to a csv file.
I'm scraping two things from each reviewer: Review score AND written review
I'd like to write the review score into the first column, and the written review into the second column. However, writerow only does it row by row.
Appreciate any help on this! :)
import os, requests, csv
from bs4 import BeautifulSoup
# Get URL of the page
URL = ('https://www.tripadvisor.com/Attraction_Review-g294265-d2149128-Reviews-Gardens_by_the_Bay-Singapore.html')
with open('GardensbytheBay.csv', 'w', newline='') as csvfile:
writer = csv.writer(csvfile)
# Looping until the 5th page of reviews
for pagecounter in range(3):
# Request get the first page
res = requests.get(URL)
res.raise_for_status
# Download the html of the first page
soup = BeautifulSoup(res.text, "html.parser")
# Match it to the specific tag for all 5 ratings
reviewElems = soup.findAll('img', {'class': ['sprite-rating_s_fill rating_s_fill s50', 'sprite-rating_s_fill rating_s_fill s40', 'sprite-rating_s_fill rating_s_fill s30', 'sprite-rating_s_fill rating_s_fill s20', 'sprite-rating_s_fill rating_s_fill s10']})
reviewWritten = soup.findAll('p', {'class':'partial_entry'})
if reviewElems:
for row, rows in zip(reviewElems, reviewWritten):
review_text = row.attrs['alt'][0]
review2_text = rows.get_text(strip=True).encode('utf8', 'ignore').decode('latin-1')
writer.writerow([review_text])
writer.writerow([review2_text])
print('Writing page', pagecounter + 1)
else:
print('Could not find clue.')
# Find URL of next page and update URL
if pagecounter == 0:
nextLink = soup.select('a[data-offset]')[0]
elif pagecounter != 0:
nextLink = soup.select('a[data-offset]')[1]
URL = 'http://www.tripadvisor.com' + nextLink.get('href')
print('Download complete')
You can put the review score and text in the same row but different columns with:
writer.writerow([review_text, review2_text])
Your initial approach takes each of the items as a separate row and writes them in succession which is not what you want.
You can use pandas dataFrame:
import pandas as pd
import numpy as np
csv_file = pd.read_csv('GardensbytheBay.csv')
csv_file.insert(idx, cloname, value)
csv_input.to_csv('output.csv', index=False)
Why do I only get the results form the last url?
The idea is that I get a list of results of both urls.
Also, with the printing in csv I get eacht time an empty row. How do I remove this row?
import csv
import requests
from lxml import html
import urllib
TV_category = ["_108-tot-127-cm-43-tot-50-,98952,501090","_128-tot-150-cm-51-tot-59-,98952,501091"]
url_pattern = 'http://www.mediamarkt.be/mcs/productlist/{}.html?langId=-17'
for item in TV_category:
url = url_pattern.format(item)
page = requests.get(url)
tree = html.fromstring(page.content)
outfile = open("./tv_test1.csv", "wb")
writer = csv.writer(outfile)
rows = tree.xpath('//*[#id="category"]/ul[2]/li')
for row in rows:
price = row.xpath('normalize-space(div/aside[2]/div[1]/div[1]/div/text())')
product_ref = row.xpath('normalize-space(div/div/h2/a/text())')
writer.writerow([product_ref,price])
As I explained in the question's comments, you need to put the second for loop inside (at the end) the first one. Otherwise, only the last rows results will be saved/written to the CSV-format file.
You don't need to open the file in each loop (a with statement will close it automagically). It is, as well, important to highlight that if you open a file with write flags it will overwrite, and if it's inside a loop it will overwrite each time it's opened.
I'd refactor your code as follows:
import csv
import requests
from lxml import html
import urllib
TV_category = ["_108-tot-127-cm-43-tot-50-,98952,501090","_128-tot-150-cm-51-tot-59-,98952,501091"]
url_pattern = 'http://www.mediamarkt.be/mcs/productlist/{}.html?langId=-17'
with open("./tv_test1.csv", "wb") as outfile:
writer = csv.writer(outfile)
for item in TV_category:
url = url_pattern.format(item)
page = requests.get(url)
tree = html.fromstring(page.content)
rows = tree.xpath('//*[#id="category"]/ul[2]/li')
for row in rows:
price = row.xpath('normalize-space(div/aside[2]/div[1]/div[1]/div/text())')
product_ref = row.xpath('normalize-space(div/div/h2/a/text())')
writer.writerow([product_ref,price])