Why my code doesn't render the javascript pages using requests_html and beautifulSoup
from requests_html import HTMLSession
from bs4 import BeautifulSoup
session = HTMLSession()
def track(num):
url = f'https://www.trackingmore.com/track/en/{num}'
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:103.0) Gecko/20100101 Firefox/103.0'}
r = session.post(url,headers=headers)
# r.html.render(timeout=20)
res = []
soup = BeautifulSoup(r.content,'lxml')
st = soup.find('div',class_ ="track-status uk-flex")
print(st.text)
if st != 'Not Found':
checkpoint = soup.find_all('div', class_="info-checkpoint")
for i in checkpoint:
date = i.find('div',class_='info-date').text.strip()
desc = i.find('div',class_='info-desc').text.strip()
res.append({
'Date':date.replace('\xa0','')[:19],
'Description':desc.replace('\xa0','')
})
return res
else :
return res
The output is like this, I can't get the value inside of each javascript function
[{'Date': '{{info.Date}} {{inf', 'Description': '{{info.StatusDescription}}'}, {'Date': '{{info.Date}} {{inf', 'Description': '{{info.StatusDescription}}'}]
Related
i would like to scrape the header-element from these both links -
For me this 2 sites look absolute identical - pics see below
Why is only the scraping for the second link working and not for the first?
import time
import requests
from bs4 import BeautifulSoup
# not working
link = "https://apps.apple.com/us/app/bingo-story-live-bingo-games/id1179108009?uo=4"
page = requests.get (link)
time.sleep (1)
soup = BeautifulSoup (page.content, "html.parser")
erg = soup.find("header")
print(f"First Link: {erg}")
# working
link = "https://apps.apple.com/us/app/jackpot-boom-casino-slots/id1554995201?uo=4"
page = requests.get (link)
time.sleep (1)
soup = BeautifulSoup (page.content, "html.parser")
erg = soup.find("header")
print(f"Second Link: {len(erg)}")
Working:
Not Working:
The page is sometimes loaded by JavaScript, so request won't support it.
You can use a while loop to check if header appears in the soup and then break
import requests
from bs4 import BeautifulSoup
headers = {
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.77 Safari/537.36"
}
link = "https://apps.apple.com/us/app/bingo-story-live-bingo-games/id1179108009?uo=4"
while True:
soup = BeautifulSoup(requests.get(link).content, "html.parser")
header = soup.find("header")
if header:
break
print(header)
Try this to get whatever fields you wish to grab from those links. curently it fetches the title. You can modify res.json()['data'][0]['attributes']['name'] to grab any field of your interest. Mkae sure to put the urls within this list urls_to_scrape.
import json
import requests
from bs4 import BeautifulSoup
from urllib.parse import unquote
urls_to_scrape = {
'https://apps.apple.com/us/app/bingo-story-live-bingo-games/id1179108009?uo=4',
'https://apps.apple.com/us/app/jackpot-boom-casino-slots/id1554995201?uo=4'
}
base_url = 'https://apps.apple.com/us/app/bingo-story-live-bingo-games/id1179108009?uo=4'
link = 'https://amp-api.apps.apple.com/v1/catalog/US/apps/{}'
params = {
'platform': 'web',
'additionalPlatforms': 'appletv,ipad,iphone,mac',
'extend': 'customPromotionalText,customScreenshotsByType,description,developerInfo,distributionKind,editorialVideo,fileSizeByDevice,messagesScreenshots,privacy,privacyPolicyText,privacyPolicyUrl,requirementsByDeviceFamily,supportURLForLanguage,versionHistory,websiteUrl',
'include': 'genres,developer,reviews,merchandised-in-apps,customers-also-bought-apps,developer-other-apps,app-bundles,top-in-apps,related-editorial-items',
'l': 'en-us',
'limit[merchandised-in-apps]': '20',
'omit[resource]': 'autos',
'sparseLimit[apps:related-editorial-items]': '5'
}
with requests.Session() as s:
s.headers['User-Agent'] = 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.101 Safari/537.36'
res = s.get(base_url)
soup = BeautifulSoup(res.text,"lxml")
token_raw = soup.select_one("[name='web-experience-app/config/environment']").get("content")
token = json.loads(unquote(token_raw))['MEDIA_API']['token']
s.headers['Accept'] = 'application/json'
s.headers['Referer'] = 'https://apps.apple.com/'
s.headers['Authorization'] = f'Bearer {token}'
for url in urls_to_scrape:
id_ = url.split("/")[-1].strip("id").split("?")[0]
res = s.get(link.format(id_),params=params)
title = res.json()['data'][0]['attributes']['name']
print(title)
I'm trying to login to a website using python Request for an automation purpose. And I'm getting an error as 'str' object has no attribute 'text'
My code is
from BeautifulSoup import BeautifulSoup
logging.basicConfig(filename='app.log',level=logging.INFO)
headers = {
'user-agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
}
def post_request_curl(data):
try:
with requests.Session() as s:
login_data=data['login_details']
r = s.get(url=data['url'], headers=headers)
soup = BeautifulSoup(r.content, 'html.parser')
login_data['form_build_id'] = soup.find_all('input', attrs={'name': 'form_build_id'})['value']
r = s.post(url=data['url'], data=login_data, headers=headers)
return r
except Exception as e:
logging.error('Error occurred ' + str(e))
Try:
from bs4 import BeautifulSoup
import requests
logging.basicConfig(filename='app.log',level=logging.INFO)
headers = {
'user-agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
}
def post_request_curl(data):
try:
with requests.Session() as s:
login_data=data['login_details']
r = s.get(url=data['url'], headers=headers)
soup = BeautifulSoup(r.content, 'html.parser')
login_data['form_build_id'] = soup.find_all('input', attrs={'name': 'form_build_id'})['value']
r = s.post(url=data['url'], data=login_data, headers=headers)
return r
except Exception as e:
logging.error('Error occurred ' + str(e))
After reading a LOT, I have tried to do my first step in web scraping at yell website with urllib and requests but I get the same in both cases (404 not found).
The url is:
url = https://www.yell.com/
What I have tried:
urllib package
import urllib.request
f = urllib.request.urlopen(url)
print(f.read(100))
and
import urllib.request
opener = urllib.request.build_opener()
opener.addheaders = [('User-agent', 'Mozilla/5.0')]
opener.open(url)
requests package
url = 'www.yell.com'
response = requests.get(url)
and
headers = {'Accept': 'text/html'}
response = requests.get(url, headers=headers)
But i reach to the 404 error.
Try this using urllib
import urllib.request
url = 'https://www.yell.com/'
headers = { 'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; Win64; x64)' }
request = urllib.request.Request(url, headers=headers)
response = urllib.request.urlopen(request)
print(response.read())
I would suggest you to use requests + beautifulsoup4
https://www.crummy.com/software/BeautifulSoup/bs4/doc/
it will make your scraping life easier
#You can use also selenium to avoid http errors
from selenium import webdriver
from bs4 import BeautifulSoup
import urllib.request
main_url = 'https://www.yell.com/'
driver = webdriver.Chrome(r'write chromedriver path')
driver.get(main_url)
res = driver.execute_script("return document.documentElement.outerHTML")
soup = BeautifulSoup(res, 'html.parser')
headers = { 'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; Win64; x64)' }
request = urllib.request.Request(main_url, headers=headers)
response = urllib.request.urlopen(request)
print(response.read())
tring to extract links and want to handle loading. but not the links even.
code:
from bs4 import BeautifulSoup
import requests
r = requests.get('http://www.indiabusinessguide.in/business-categories/agriculture/agricultural-equipment.html')
soup = BeautifulSoup(r.text,'lxml')
links = soup.find_all('a',class_='link_orange')
for link in links:
print(link['href'])
please help me to handle this loading and extraction of links.
Try using the lxml library. Response is received by posting a request to the url using Requests.
import requests
import lxml
from lxml import html
contact_list = []
def scrape(url, pages):
for page in range(1, pages):
headers = {
"Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.109 Safari/537.36",
"X-Requested-With": "XMLHttpRequest",
"Cookie": "PHPSESSID=2q0tk3fi1kid0gbdfboh94ed56",
}
data = {
"page": f"{page}"
}
r = requests.post(url, headers=headers, data=data)
tree = html.fromstring(r.content)
links= tree.xpath('//a[#class="link_orange"]')
for link in links:
# print(link.get('href'))
contact_list.append(link.get('href'))
url = "http://www.indiabusinessguide.in/ajax_advertiselist.php"
scrape(url, 10)
print(contact_list)
print(len(contact_list))
In Python 3, the following code obtains the HTML source for a webpage.
import urllib.request
url = "https://docs.python.org/3.4/howto/urllib2.html"
response = urllib.request.urlopen(url)
response.read()
How can I add the following custom header to the request when using urllib.request?
headers = { 'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; Win64; x64)' }
The request headers can be customized by first creating a request object then supplying it to urlopen.
import urllib.request
url = "https://docs.python.org/3.4/howto/urllib2.html"
hdr = { 'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; Win64; x64)' }
req = urllib.request.Request(url, headers=hdr)
response = urllib.request.urlopen(req)
response.read()
Source: Python 3.4 Documentation
import urllib.request
opener = urllib.request.build_opener()
opener.addheaders = [('User-agent', 'Mozilla/5.0')]
urllib.request.install_opener(opener)
response = urllib.request.urlopen("url")
response.read()
Should you wish to learn about the details you can refer to the python documentation: https://docs.python.org/3/library/urllib.request.html
#Using urllib.request, with urlopen, allows to open the specified URL.
#Headers can be included inside the urlopen along with the url.
from urllib.request import urlopen
url = "https://docs.python.org/3.4/howto/urllib2.html"
header = { 'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; Win64; x64)' }
response = urlopen(url, headers=header)
response.read()