Trouble with webscraping - python

I would like to have the name of the hotel, usually I have no problem with this kind of scraping but here it doesn't work I don't understand.
Here's my script:
import numpy as np
import time
from random import randint
import requests
from requests import get
from bs4 import BeautifulSoup
import pandas as pd
import re
import random
#headers= {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.47 Safari/537.36'}
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:78.0) Gecko/20100101 Firefox/78.0',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Language': 'fr,fr-FR;q=0.8,en-US;q=0.5,en;q=0.3',
'Referer': 'https://www.espncricinfo.com/',
'Upgrade-Insecure-Requests': '1',
'Connection': 'keep-alive',
'Pragma': 'no-cache',
'Cache-Control': 'no-cache',
}
url = 'https://www.booking.com/hotel/fr/hyatt-regency-paris-etoile.fr.html?label=gen173nr-1DCA0oTUIMZWx5c2Vlc3VuaW9uSA1YBGhNiAEBmAENuAEXyAEM2AED6AEB-AECiAIBqAIDuAL_5ZqEBsACAdICJDcxYjgyZmI2LTFlYWQtNGZjOS04Y2U2LTkwNTQyZjI5OWY1YtgCBOACAQ;sid=303509179a2849df63e4d1e5bc1ab1e3;dest_id=-1456928;dest_type=city;dist=0;group_adults=2;group_children=0;hapos=1;hpos=1;no_rooms=1;room1=A%2CA;sb_price_type=total;sr_order=popularity;srepoch=1619708145;srpvid=6f6268f8305e011d;type=total;ucfs=1&#hotelTmpl'
results = requests.get(url, headers = headers)
soup = BeautifulSoup(results.text, "html.parser")
hotel = soup.find('h2', class_ = 'hp__hotel-name').text
print(hotel)
Here's the error :
Traceback (most recent call last):
File "test_booking_info_supp.py", line 75, in <module>
hotel = soup.find('h2', class_ = 'hp__hotel-name').text
AttributeError: 'NoneType' object has no attribute 'text'
I cannot understand why I obtained None, here's the html:
The link to the website is in the image

You can try out with id attribute from tag to get the text value
url = 'https://www.booking.com/hotel/fr/hyatt-regency-paris-etoile.fr.html?label=gen173nr-1DCA0oTUIMZWx5c2Vlc3VuaW9uSA1YBGhNiAEBmAENuAEXyAEM2AED6AEB-AECiAIBqAIDuAL_5ZqEBsACAdICJDcxYjgyZmI2LTFlYWQtNGZjOS04Y2U2LTkwNTQyZjI5OWY1YtgCBOACAQ;sid=303509179a2849df63e4d1e5bc1ab1e3;dest_id=-1456928;dest_type=city;dist=0;group_adults=2;group_children=0;hapos=1;hpos=1;no_rooms=1;room1=A%2CA;sb_price_type=total;sr_order=popularity;srepoch=1619708145;srpvid=6f6268f8305e011d;type=total;ucfs=1&#hotelTmpl'
results = requests.get(url)
soup = BeautifulSoup(results.text, "html.parser")
hotel = soup.find("h2",attrs={"id":"hp_hotel_name"})
print(hotel.text.strip("\n").split("\n")[1])
Output:
'Hyatt Regency Paris Etoile'

Related

How to change Json data output in table format

import requests
from pprint import pprint
import pandas as pd
baseurl = "https://www.nseindia.com/"
url = f'https://www.nseindia.com/api/live-analysis-oi-spurts-underlyings'
headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, '
'like Gecko) '
'Chrome/80.0.3987.149 Safari/537.36',
'accept-language': 'en,gu;q=0.9,hi;q=0.8', 'accept-encoding': 'gzip, deflate, br'}
session = requests.Session()
request = session.get(baseurl, headers=headers, timeout=30)
cookies = dict(request.cookies)
res = session.get(url, headers=headers, timeout=30, cookies=cookies)
print(res.json())
I tried df = pd.DataFrame(res.json()) but couldn't get data in table format. How to do that Plz. Also how to select few particular columns only in data output instead of all columns.
Try this :
import json
import codecs
df = pd.DataFrame(json.loads(codecs.decode(bytes(res.text, 'utf-8'), 'utf-8-sig'))['data'])
And to select a specific columns, you can use :
mini_df = df[['symbol', 'latestOI', 'prevOI', 'changeInOI', 'avgInOI']]
>>> print(mini_df)

Why does soup.findAll return []?

I am having trouble reading data from a url with BeautifulSoup
This is my code:
url1 = "https://www.barstoolsportsbook.com/events/1018282280"
from bs4 import BeautifulSoup
import requests
headers = {
'User-agent':
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36 Edge/18.19582"
}
html = requests.get(url1, headers=headers)
soup = BeautifulSoup(html.text, 'lxml')
data = soup.findAll('div',attrs={"class":"section"})
print(data)
#for x in data:
# print(x.find('p').text)
When I print(data) I am returned []. What could be the reason for this? I would like to avoid using selenium for this task if possible.
This is the HTML for what I'm trying to grab
<div data-v-50e01018="" data-v-2a52296d="" class="section"><p data-v-5f665d29="" data-v-50e01018="" class="header strongbody2">HOT TIPS</p><p data-v-5f665d29="" data-v-50e01018="" class="tip body2"> The Mets have led after 3 innings in seven of their last nine night games against NL East Division opponents that held a losing record. </p><p data-v-5f665d29="" data-v-50e01018="" class="tip body2"> The 'Inning 1 UNDER 0.5 runs' market has hit in each of the Marlins' last nine games against NL East opponents. </p></div>
You can likely get what you want with this request:
import requests
headers = {
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:103.0) Gecko/20100101 Firefox/103.0',
'Accept': 'application/json, text/plain, */*',
'Accept-Language': 'en-US,en;q=0.5',
'Authorization': 'Basic MTI2OWJlMjItNDI2My01MTI1LWJlNzMtMDZmMjlmMmZjNWM3Omk5Zm9jajRJQkZwMUJjVUc0NGt2S2ZpWEpremVKZVpZ',
'Origin': 'https://www.barstoolsportsbook.com',
'DNT': '1',
'Connection': 'keep-alive',
'Referer': 'https://www.barstoolsportsbook.com/',
'Sec-Fetch-Dest': 'empty',
'Sec-Fetch-Mode': 'cors',
'Sec-Fetch-Site': 'cross-site',
}
response = requests.get('https://api.isportgenius.com.au/preview/1018282280', headers=headers)
response.json()
You should browse the network tab to see where the rest of the data is coming from, or use a webdriver.

Parsing a table with Pandas

I am trying to parse the table from https://alreits.com/screener
I have tried this:
main_url = 'https://alreits.com/screener'
r = requests.get(main_url)
df_list = pd.read_html(r.text)
df = df_list[0]
print(df)
but pandas cant find the table.
I have also tried using BeautifulSoup4 but it didnt seem to give better results.
This is the selector: #__next > div.MuiContainer-root.MuiContainer-maxWidthLg > div.MuiBox-root.jss9.Card__CardContainer-feksr6-0.fpbzHQ.ScreenerTable__CardContainer-sc-1c5wxgl-0.GRrTj > div > table > tbody
This is the full xPath: /html/body/div/div[2]/div[2]/div/table/tbody
I am trying to get the Stock symbol (under name),sector,score and market cap. The other data would be nice to have but is not necessary.
Thank You!
I found one JSON url from the dev tool. This is an easy way to extract the table instead of using selenium. Use post request to extract the data.
import requests
headers = {
'authority': 'api.alreits.com:8080',
'sec-ch-ua': '"Google Chrome";v="93", " Not;A Brand";v="99", "Chromium";v="93"',
'sec-ch-ua-mobile': '?0',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.63 Safari/537.36',
'sec-ch-ua-platform': '"Windows"',
'content-type': 'application/json',
'accept': '*/*',
'origin': 'https://alreits.com',
'sec-fetch-site': 'same-site',
'sec-fetch-mode': 'cors',
'sec-fetch-dest': 'empty',
'referer': 'https://alreits.com/',
'accept-language': 'en-US,en;q=0.9',
}
params = (
('page', '0'),
('size', '500'),
('sort', ['marketCap,desc', 'score,desc', 'ffoGrowth,desc']),
)
data = '{"filters":[]}'
response = requests.post('https://api.alreits.com:8080/api/reits/screener', headers=headers, params=params, data=data)
df = pd.DataFrame(response.json())
The code below will return the data you are looking for.
import requests
import pprint
import json
headers = {'content-type': 'application/json',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36'}
r = requests.post(
'https://api.alreits.com:8080/api/reits/screener?page=0&size=500&sort=marketCap,desc&sort=score,desc&sort=ffoGrowth,desc',
headers=headers, data=json.dumps({'filters':[]}))
if r.status_code == 200:
pprint.pprint(r.json())
# Now you have the data - do what you want with it
else:
print(r.status_code)

Scraping with requests

what is wrong in my code, I try get the same content like in https://koleo.pl/rozklad-pkp/krakow-glowny/radom/19-03-2019_10:00/all/EIP-IC--EIC-EIP-IC-KM-REG but result is diffrent as I want to have.
import requests
from bs4 import BeautifulSoup
s = requests.Session()
s.headers.update({"User-Agent": 'Mozilla/5.0 (Windows NT 10.0; Win64; x64)
AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.186 Safari/537.36'})
response=s.get('https://koleo.pl/rozklad-pkp/krakow-glowny/radom/19-03-
2019_10:00/all/EIP-IC--EIC-EIP-IC-KM-REG')
soup=BeautifulSoup(response.text,'lxml')
print(soup.prettify())
You can use requests and pass params in to get json for the train info and prices. I haven't parsed out all the info as this is just to show you it is possible. I parse out the train ids to be able to make the subsequent requests from price info which are linked by ids to the train info
import requests
from bs4 import BeautifulSoup as bs
url = 'https://koleo.pl/pl/connections/?'
headers = {
'Accept' : 'application/json, text/javascript, */*; q=0.01',
'Accept-Encoding' : 'gzip, deflate, br',
'Accept-Language' : 'en-US,en;q=0.9',
'Connection' : 'keep-alive',
'Cookie' : '_ga=GA1.2.2048035736.1553000429; _gid=GA1.2.600745193.1553000429; _gat=1; _koleo_session=bkN4dWRrZGx0UnkyZ3hjMWpFNGhiS1I3TzhQMGNyWitvZlZ0QVRUVVVtWUFPMUwxL0hJYWJyYnlGTUdHYXNuL1N6QlhHMHlRZFM3eFZFcjRuK3ZubllmMjdSaU5CMWRBSTFOc1JRc2lDUGV0Y2NtTjRzbzZEd0laZWI1bjJoK1UrYnc5NWNzZzNJdXVtUlpnVE15QnRnPT0tLTc1YzV1Q2xoRHF4VFpWWTdWZDJXUnc9PQ%3D%3D--3b5fe9bb7b0ce5960bc5bd6a00bf405df87f8bd4',
'Host' : 'koleo.pl',
'Referer' : 'https://koleo.pl/rozklad-pkp/krakow-glowny/radom/19-03-2019_10:00/all/EIP-IC--EIC-EIP-IC-KM-REG',
'User-Agent' : 'Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36',
'X-CSRF-Token' : 'heag3Y5/fh0hyOfgdmSGJBmdJR3Perle2vJI0VjB81KClATLsJxFAO4SO9bY6Ag8h6IkpFieW1mtZbD4mga7ZQ==',
'X-Requested-With' : 'XMLHttpRequest'
}
params = {
'v' : 'a0dec240d8d016fbfca9b552898aba9c38fc19d5',
'query[date]' : '19-03-2019 10:00:00',
'query[start_station]' : 'krakow-glowny',
'query[end_station]': 'radom',
'query[brand_ids][]' : '29',
'query[brand_ids][]' : '28',
'query[only_direct]' : 'false',
'query[only_purchasable]': 'false'
}
with requests.Session() as s:
data= s.get(url, params = params, headers = headers).json()
print(data)
priceUrl = 'https://koleo.pl/pl/prices/{}?v=a0dec240d8d016fbfca9b552898aba9c38fc19d5'
for item in data['connections']:
r = s.get(priceUrl.format(item['id'])).json()
print(r)
You have to use selenium in order to get that dynamically generated content. And then you can parse html with BS. For example I've parsed dates:
from bs4 import BeautifulSoup
from selenium import webdriver
driver = webdriver.Firefox()
driver.get('https://koleo.pl/rozklad-pkp/krakow-glowny/radom/19-03-2019_10:00/all/EIP-IC--EIC-EIP-IC-KM-REG')
soup = BeautifulSoup(driver.page_source, 'lxml')
for div in soup.findAll("div", {"class": 'date custom-panel'}):
date = div.findAll("div", {"class": 'row'})[0].string.strip()
print(date)
Output:
wtorek, 19 marca
środa, 20 marca

Extract json content in <script using BeautifulSoup

I'm trying to extract a json part of the script using beautiful soup but it prints Nothing. What's wrong?
import requests,json
from bs4 import BeautifulSoup
headers = {
'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36',
'referrer': 'https://google.com',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate, br',
'Accept-Language': 'en-US,en;q=0.9',
'Pragma': 'no-cache',
}
r = requests.get('https://www.joox.com/id/id/single/xtMtD9ZdeLEdHp1w1fip8w==',headers=headers)
soup = BeautifulSoup(r.content, 'html5lib')
data = json.loads(soup.find('script').text)
print(data)
The soup result is like:
<script>
__NEXT_DATA__ = {"props":{"trackData":{"album_url":"https://imgcache.qq.com/music/photo/mid_album_300/O/F/002tkoBZ2zJPOF.jpg","code":0,"country":"hk","encodeSongId":"xtMtD9ZdeLEdHp1w1fip8w==","express_domain":"http://stream.music.joox.com/","flag":0,"gososo":0,"has_hifi":false,"has_hq":false,"imgSrc":"https://imgcache.qq.com/music/photo/mid_album_300/O/F/002tkoBZ2zJPOF.jpg","kbps_map":"{\"128\":4082449,\"192\":6522038,\"24\":825973,\"320\":10216761,\"48\":1708095,\"96\":3701266,\"ape\":0,\"flac\":0}\n","ktrack_id":0,"m4aUrl":"https://hk.stream.music.joox.com/C4000035Jew421IKj2.m4a?
Any ideas for this? thanks
You can use substring and regular expression for obtaining what you are seeking for.
import requests,json, re
from bs4 import BeautifulSoup
headers = {
'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36',
'referrer': 'https://google.com',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate, br',
'Accept-Language': 'en-US,en;q=0.9',
'Pragma': 'no-cache',
}
r = requests.get('https://www.joox.com/id/id/single/xtMtD9ZdeLEdHp1w1fip8w==',headers=headers)
soup = BeautifulSoup(r.content, 'html5lib')
# finding the script element whihc contains the required data
json_data = soup.find('script', text=re.compile("__NEXT_DATA__") )
# identifying the required elements and obtaining it by sub string
data = str(json_data)[str(json_data).find('__NEXT_DATA__ = '):str(json_data).find('module={}')]
data = json.loads(data.replace('__NEXT_DATA__ = ', ''))
print(data)
Using slicing technique we are identifying the string pattern and extracting the json string alone. After that you are good to go!
Hope this helps! Cheers!
even BeautifulSoup still need Regex, why not use it directly
import re
....
r = requests.get('https://www.joox.com/id/id/single/xtMtD9ZdeLEdHp1w1fip8w==',headers=headers)
jsData = re.search(r'__NEXT_DATA__\s+=\s+(.*)', r.text)
data = json.loads(jsData.group(1))
print(data)

Categories

Resources