I am trying to get data from a site that has the following form: "http://www.mysite.here?pageNo=2"
How do I get the html data from a consecutive range of pages using Urllib2 and/or BeautifulSoup? This code returns the html only for the first page.
import urllib2
from bs4 import BeautifulSoup
for x in range(1,450):
numb = str(x)
url = "http://www.mysite.here?pageNo="+numb
page = urllib2.urlopen(url).read()
soup = BeautifulSoup(page, "html.parser")
Print soup
On each iteration you create new variable with name soup.
You need to create storage for all pages - list with pages. And append to it on each iteration.
import urllib2
from bs4 import BeautifulSoup
pages = []
for x in range(1, 450):
numb = str(x)
url = "http://www.mysite.here?pageNo=" + numb
page = urllib2.urlopen(url).read()
pages.append(BeautifulSoup(page, "html.parser"))
print pages
You can create an array soup = [] and add to it with soup.append(soup).
If you want just one soup object, you need to add the contents at each step, for instance for the body's
soup = BeautifulSoup("<html><body></body></body>") # initialize soup
for x in range(1,450):
numb = str(x)
url = "http://www.mysite.here?pageNo="+numb
page = urllib2.urlopen(url).read()
tmpsoup = BeautifulSoup(page, "html.parser")
for element in tmpsoup.body:
soup.body.append(element)
Related
This is the link url
url = 'https://www.booking.com/searchresults.html?label=gen173nr-1FCAEoggI46AdIM1gEaGyIAQGYATG4ARfIAQzYAQHoAQH4AQKIAgGoAgO4AuS4sJ4GwAIB0gIkYWJlYmZiMWItNWJjMi00M2Y2LTk3MGUtMzI2ZGZmMmIyNzMz2AIF4AIB&aid=304142&dest_id=-2092174&dest_type=city&group_adults=2&req_adults=2&no_rooms=1&group_children=0&req_c
Hotel_name = doc.find_all("div",{'class' : "fcab3ed991 a23c043802"})
this gives me the result of all hotel names in page number, 1, but how can I get the hotel names of all the pages?
I've tried this
import requests
from bs4 import BeautifulSoup
# Initialize the page number
page_number = 0
while True:
# Increment the page number
page_number += 1
# Make the GET request to the URL
url = f"https://www.booking.com/searchresults.html?label=gen173nr-1FCAEoggI46AdIM1gEaGyIAQGYATG4ARfIAQzYAQHoAQH4AQKIAgGoAgO4AuS4sJ4GwAIB0gIkYWJlYmZiMWItNWJjMi00M2Y2LTk3MGUtMzI2ZGZmMmIyNzMz2AIF4AIB&aid=304142&dest_id=-2092174&dest_type=city&group_adults=2&req_adults=2&no_rooms=1&group_children=0&req_children=0&nflt=ht_id%3D204&rows=15&offset={page_number*15}"
response = requests.get(url)
# Parse the HTML content
soup = BeautifulSoup(response.content, 'html.parser')
# Extract the hotel information
hotels = soup.find_all('div', {'class' : "fcab3ed991 a23c043802"})
if not hotels:
break
for hotel in hotels:
price = hotel.find('div', {' data-testid="title'}).text
print(f"{price}")
but it gives me an empty list as an output.
Avoid selecting elements by classes that looks highly dynamic and use HTML structure instead. Check the number of total results and use it in range() to iterate the results.
Example
import requests, re
from bs4 import BeautifulSoup
data = []
soup = BeautifulSoup(
requests.get('https://www.booking.com/searchresults.html?label=gen173nr-1FCAEoggI46AdIM1gEaGyIAQGYATG4ARfIAQzYAQHoAQH4AQKIAgGoAgO4AuS4sJ4GwAIB0gIkYWJlYmZiMWItNWJjMi00M2Y2LTk3MGUtMzI2ZGZmMmIyNzMz2AIF4AIB&aid=304142&dest_id=-2092174&dest_type=city&group_adults=2&req_adults=2&no_rooms=1&group_children=0&req_children=0&nflt=ht_id%3D204&rows=15',
headers={'user-agent':'some agent'}
).text)
num_results = int(re.search(r'\d+',soup.select_one('div:has(+[data-testid="pagination"])').text).group(0))
for i in range(0,int(num_results/25)):
soup = BeautifulSoup(
requests.get(f'https://www.booking.com/searchresults.html?label=gen173nr-1FCAEoggI46AdIM1gEaGyIAQGYATG4ARfIAQzYAQHoAQH4AQKIAgGoAgO4AuS4sJ4GwAIB0gIkYWJlYmZiMWItNWJjMi00M2Y2LTk3MGUtMzI2ZGZmMmIyNzMz2AIF4AIB&aid=304142&dest_id=-2092174&dest_type=city&group_adults=2&req_adults=2&no_rooms=1&group_children=0&req_children=0&nflt=ht_id%3D204&rows=15&offset={int(i*25)}',
headers={'user-agent':'some agent'}
).text
)
data.extend([e.select_one('[data-testid="title"]').text for e in soup.select('[data-testid="property-card"]')])
data
Hey guess so I got as far as being able to add the a class to a list. The problem is I just want the href link to be added to the links_with_text list and not the entire a class. What am I doing wrong?
from bs4 import BeautifulSoup
from requests import get
import requests
URL = "https://news.ycombinator.com"
page = requests.get(URL)
soup = BeautifulSoup(page.content, 'html.parser')
results = soup.find(id = 'hnmain')
articles = results.find_all(class_="title")
links_with_text = []
for article in articles:
link = article.find('a', href=True)
links_with_text.append(link)
print('\n'.join(map(str, links_with_text)))
This prints exactly how I want the list to print but I just want the href from every a class not the entire a class. Thank you
To get all links from the https://news.ycombinator.com, you can use CSS selector 'a.storylink'.
For example:
from bs4 import BeautifulSoup
from requests import get
import requests
URL = "https://news.ycombinator.com"
page = requests.get(URL)
soup = BeautifulSoup(page.content, 'html.parser')
links_with_text = []
for a in soup.select('a.storylink'): # <-- find all <a> with class="storylink"
links_with_text.append(a['href']) # <-- note the ['href']
print(*links_with_text, sep='\n')
Prints:
https://blog.mozilla.org/futurereleases/2020/06/18/introducing-firefox-private-network-vpns-official-product-the-mozilla-vpn/
https://mxb.dev/blog/the-return-of-the-90s-web/
https://github.blog/2020-06-18-introducing-github-super-linter-one-linter-to-rule-them-all/
https://www.sciencemag.org/news/2018/11/why-536-was-worst-year-be-alive
https://www.strongtowns.org/journal/2020/6/16/do-the-math-small-projects
https://devblogs.nvidia.com/announcing-cuda-on-windows-subsystem-for-linux-2/
https://lwn.net/SubscriberLink/822568/61d29096a4012e06/
https://imil.net/blog/posts/2020/fakecracker-netbsd-as-a-function-based-microvm/
https://jepsen.io/consistency
https://tumblr.beesbuzz.biz/post/621010836277837824/advice-to-young-web-developers
https://archive.org/search.php?query=subject%3A%22The+Navy+Electricity+and+Electronics+Training+Series%22&sort=publicdate
https://googleprojectzero.blogspot.com/2020/06/ff-sandbox-escape-cve-2020-12388.html?m=1
https://apnews.com/1da061ce00eb531291b143ace0eed1c9
https://support.apple.com/library/content/dam/edam/applecare/images/en_US/appleid/android-apple-music-account-payment-none.jpg
https://standpointmag.co.uk/issues/may-june-2020/the-healing-power-of-birdsong/
https://steveblank.com/2020/06/18/the-coming-chip-wars-of-the-21st-century/
https://www.videolan.org/security/sb-vlc3011.html
https://onesignal.com/careers/2023b71d-2f44-4934-a33c-647855816903
https://www.bbc.com/news/world-europe-53006790
https://github.com/efficient/HOPE
https://everytwoyears.org/
https://www.historytoday.com/archive/natural-histories/intelligence-earthworms
https://cr.yp.to/2005-590/powerpc-cwg.pdf
https://quantum.country/
http://www.crystallography.net/cod/
https://parkinsonsnewstoday.com/2020/06/17/tiny-magnetically-powered-implant-may-be-future-of-deep-brain-stimulation/
https://spark.apache.org/releases/spark-release-3-0-0.html
https://arxiv.org/abs/1712.09624
https://www.washingtonpost.com/technology/2020/06/18/data-privacy-law-sherrod-brown/
https://blog.chromium.org/2020/06/improving-chromiums-browser.html
I am trying to get all blog titles from every page on a blog but so far am only able to produce output from the last page on that blog
from urllib.request import urlopen
from bs4 import BeautifulSoup
base_url = 'http://www.madame-love.com'
n = 10
for i in range(2, n+1):
html = urlopen(base_url + "/page/%d" % i)
page = BeautifulSoup(html.read(), 'html.parser')
for titles in page.findAll('h2'):
print(titles.string)
Try this. It will give you all the titles across different pages:
import requests
from bs4 import BeautifulSoup
base_url = 'http://www.madame-love.com/page/{}/'
for link in [base_url.format(page) for page in range(1,5)]: #just input the highest page number in place of 5
res = requests.get(link)
soup = BeautifulSoup(res.text, 'lxml')
for titles in soup.select('h2.entry-title a'):
print(titles.text)
I'm scraping from two URLs that have the same DOM structure, and so I'm trying to find a way to scrape both of them at the same time.
The only caveat is that the data scraped from both these pages need to end up on distinctly named lists.
To explain with example, here is what I've tried:
import os
import requests
from bs4 import BeautifulSoup as bs
urls = ['https://www.basketball-reference.com/leaders/ws_career.html',
'https://www.basketball-reference.com/leaders/ws_per_48_career.html',]
ws_list = []
ws48_list = []
categories = [ws_list, ws48_list]
for url in urls:
response = requests.get(url, headers=headers)
soup = bs(response.content, 'html.parser')
section = soup.find('table', class_='stats_table')
for a in section.find_all('a'):
player_name = a.text
for cat_list in categories:
cat_list.append(player_name)
print(ws48_list)
print(ws_list)
This ends up printing two identical lists when I was shooting for 2 lists unique to its page.
How do I accomplish this? Would it be better practice to code it another way?
Instead of trying to append to already existing lists. Just create new ones. Make a function to do the scrape and pass each url in turn to it.
import os
import requests
from bs4 import BeautifulSoup as bs
urls = ['https://www.basketball-reference.com/leaders/ws_career.html',
'https://www.basketball-reference.com/leaders/ws_per_48_career.html',]
def parse_page(url, headers={}):
response = requests.get(url, headers=headers)
soup = bs(response.content, 'html.parser')
section = soup.find('table', class_='stats_table')
return [a.text for a in section.find_all('a')]
ws_list, ws48_list = [parse_page(url) for url in urls]
print('ws_list = %r' % ws_list)
print('ws8_list = %r' % ws48_list)
Just add them to the appropriate list and the problem is solved?
for i, url in enumerate(urls):
response = requests.get(url)
soup = bs(response.content, 'html.parser')
section = soup.find('table', class_='stats_table')
for a in section.find_all('a'):
player_name = a.text
categories[i].append(player_name)
print(ws48_list)
print(ws_list)
You can use a function to define your scraping logic, then just call it for your urls.
import os
import requests
from bs4 import BeautifulSoup as bs
def scrape(url):
response = requests.get(url)
soup = bs(response.content, 'html.parser')
section = soup.find('table', class_='stats_table')
names = []
for a in section.find_all('a'):
player_name = a.text
names.append(player_name)
return names
ws_list = scrape('https://www.basketball-reference.com/leaders/ws_career.html')
ws48_list = scrape('https://www.basketball-reference.com/leaders/ws_per_48_career.html')
print(ws_list)
print(ws48_list)
I have a problem with the following code and I am sorry, I am new to this all, I want to add the strings in the FullPage list to the actual URL and then I want to visit them and scrape some data from the pages. So far, It has been good but I do not know how to make it visit the other links in the list.
The output will only give me the data of one page but I need the data for 30 pages, how can I make this program to go over each link?
The URL has a pattern, the first part has 'http://arduinopak.com/Prd.aspx?Cat_Name=' and then the second part has the product category name.
import urllib2
from bs4 import BeautifulSoup
FullPage = ['New-Arrivals-2017-6', 'Big-Sales-click-here', 'Arduino-Development-boards',
'Robotics-and-Copters']
urlp1 = "http://www.arduinopak.com/Prd.aspx?Cat_Name="
URL = urlp1 + FullPage[0]
for n in FullPage:
URL = urlp1 + n
page = urllib2.urlopen(URL)
bsObj = BeautifulSoup(page, "html.parser")
descList = bsObj.findAll('div', attrs={"class": "panel-default"})
for desc in descList:
print(desc.getText(separator=u' '))
import urllib2
from bs4 import BeautifulSoup
FullPage = ['New-Arrivals-2017-6', 'Big-Sales-click-here', 'Arduino-Development-boards',
'Robotics-and-Copters']
urlp1 = "http://www.arduinopak.com/Prd.aspx?Cat_Name="
URL = urlp1 + FullPage[0]
for n in FullPage:
URL = urlp1 + n
page = urllib2.urlopen(URL)
bsObj = BeautifulSoup(page, "html.parser")
descList = bsObtTj.findAll('div', attrs={"class": "panel-default"})
for desc in descList:
print(desc.geext(separator=u' '))
If you want to scape each links then moving last 3 lines of your code into loop will do it.
Your current code fetches all the links but it stores only one BeautifulSoup object reference. You could instead store them all in the array or process them before visiting another URL (as shown below).
for n in FullPage:
URL = urlp1 + n
page = urllib2.urlopen(URL)
bsObj = BeautifulSoup(page, "html.parser")
descList = bsObj.findAll('div', attrs={"class": "panel-default"})
for desc in descList:
print(desc.getText(separator=u' '))
Also, note that the names using PascalCase are by convention reserved for classes. FullPage would usually be written as fullPage or FULL_PAGE if it's meant to be constant.