I'm trying to extract text using beautifulsoup or requests from this facebook page https://www.facebook.com/marketplace/item/1612977352197759/
the text is the item description, the text before the map:
this is what i've tried till now but not working :
import requests
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from lxml import html
opt = Options()
opt.add_argument("--disable-infobars")
opt.add_argument("start-maximized")
# Pass the argument 1 to allow and 2 to block
opt.add_experimental_option("prefs", {
"profile.default_content_setting_values.media_stream_mic": 2,
"profile.default_content_setting_values.media_stream_camera": 2,
"profile.default_content_setting_values.geolocation": 2,
"profile.default_content_setting_values.notifications": 2
})
global driver
driver = webdriver.Chrome(chromedriver)
driver.get('https://www.google.com')
page = requests.get('https://www.facebook.com/marketplace/item/1612977352197759/?ref=messenger_banner')
tree = html.fromstring(page.content)
print(tree)
link = tree.xpath("//span[contains(string(),'hello')]")
print(link)
Try this:
import requests
from bs4 import BeautifulSoup
import re
page = requests.get('https://www.facebook.com/marketplace/item/1612977352197759/?ref=messenger_banner')
soup = BeautifulSoup(page.text,'lxml')
span = soup.find("span",string=re.compile(".*hello.*"))
print(span)
Do let me know if this works.
Related
I have been trying to web scrape from this website: https://octane.gg/events/e83e-rlcs-x-championship-europe/stats/players
I want to get specific ratings but i get nothing when i execute this code:
from bs4 import BeautifulSoup
import requests
result = requests.get("https://octane.gg/events/e83e-rlcs-x-championship-europe/stats/players")
src = result.content
soup = BeautifulSoup(src, 'lxml')
match = soup.find('div', class_='css-gm45eu')
print(match)
output: None
How can I scrape what is in that class?
Try to use Selenium:
from selenium import webdriver
driver = webdriver.Chrome('PATH_TO --> chromedriver.exe')
driver.get("https://octane.gg/events/e83e-rlcs-x-championship-europe/stats/players")
ratings = driver.find_elements_by_xpath('//div[#class="css-gm45eu"]')
ratings_list = []
for p in range(len(ratings)):
ratings_list.append(ratings[p].text)
print(ratings_list)
Output:
['1.189', '1.109', '1.098', '1.031', '1.028', '1.005', '0.990', '0.981', '0.967', '0.936', '0.904', '0.846', '0.841', '0.840', '0.836', '0.809', '0.759', '0.726']
Download chromedriver.exe:
https://chromedriver.chromium.org/downloads
if you don't want a chrome window to open while running, use this code:
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
options = Options()
options.add_argument('--headless')
driver = webdriver.Chrome('PATH_TO --> chromedriver.exe', options=options)
driver.get("https://octane.gg/events/e83e-rlcs-x-championship-europe/stats/players")
ratings = driver.find_elements_by_xpath('//div[#class="css-gm45eu"]')
ratings_list = []
for p in range(len(ratings)):
ratings_list.append(ratings[p].text)
print(ratings_list)
For below mentioned website, I am trying to find the name and its corresponding link from that site. But not able to pass/get the data at all.
Using BeautifulSoup
from bs4 import BeautifulSoup
import requests
source = requests.get('https://mommypoppins.com/events/115/los-angeles/all/tag/all/age/all/all/deals/0/near/0/0')
soup = BeautifulSoup(source.text, 'html.parser')
mains = soup.find_all("div", {"class": "list-container-wrapper"})
name = []
lnks = []
for main in mains:
name.append(main.find("a").text)
lnks.append(main.find("a").get('href'))
Using Selenium webdriver
from selenium import webdriver
driver = webdriver.Chrome(executable_path=r"chromedriver_win32\chromedriver.exe")
driver.get("https://mommypoppins.com/events/115/los-angeles/all/tag/all/age/all/all/deals/0/near/0/0")
lnks = []
name = []
for a in driver.find_elements_by_class_name('ng-star-inserted'):
link = a.get_attribute('href')
lnks.append(link)
nm = driver.find_element_by_css_selector("#list-item-0 > div > h2 > a").text
name.append(nm)
I have tried with both 2 above methods.
Example:
name = ['Friday Night Flicks Drive-In at the Roadium', 'Open: Butterfly Pavilion and Nature Gardens']
lnks = ['https://mommypoppins.com/los-angeles-kids/event/in-person/friday-night-flicks-drive-in-at-the-roadium','https://mommypoppins.com/los-angeles-kids/event/in-person/open-butterfly-pavilion-and-nature-gardens']
Here's solution for webdriver:
import time
from selenium import webdriver
from selenium.webdriver.common.by import By
driver = webdriver.Chrome()
driver.get('https://mommypoppins.com/events/115/los-angeles/all/tag/all/age/all/all/deals/0/near/0/0')
time.sleep(3)
elements = driver.find_elements(By.XPATH, "//a[#angularticsaction='expanded-detail']")
attributes = [{el.text: el.get_attribute('href')} for el in elements]
print(attributes)
print(len(attributes))
driver.quit()
Here's solution with webdriver and bs4:
import time
from selenium import webdriver
from bs4 import BeautifulSoup
driver = webdriver.Chrome()
driver.get('https://mommypoppins.com/events/115/los-angeles/all/tag/all/age/all/all/deals/0/near/0/0')
time.sleep(3)
soup = BeautifulSoup(driver.page_source, 'html.parser')
mains = soup.find_all("a", {"angularticsaction": "expanded-detail"})
attributes = [{el.text: el.get('href')} for el in mains]
print(attributes)
print(len(attributes))
driver.quit()
Here's solution with requests:
import requests
url = "https://mommypoppins.com"
response = requests.get(f"{url}/contentasjson/custom_data/events_ng-block_1x/0/115/all/all/all/all/all").json()
attributes = [{r.get('node_title'): f"{url}{r['node'][r['nid']]['node_url']}"} for r in response['results']]
print(attributes)
print(len(attributes))
cheers!
The website is loaded dynamically, therefore requests won't support it. However, the data is available in JSON format via sending a GET request to:
https://mommypoppins.com/contentasjson/custom_data/events_ng-block_1x/0/115/all/all/all/all/all.
There's no need for BeautifulSoup or Selenium, using merely requests would work, which will make your code much faster.
import requests
URL = "https://mommypoppins.com/contentasjson/custom_data/events_ng-block_1x/0/115/all/all/all/all/all"
BASE_URL = "https://mommypoppins.com"
response = requests.get(URL).json()
names = []
links = []
for json_data in response["results"]:
data = json_data["node"][json_data["nid"]]
names.append(data["title"])
links.append(BASE_URL + data["node_url"])
I am trying to scrape code from a faceit room, this is what i've tried but it doesn't work.
Any help is much appreciated!
import requests
from bs4 import BeautifulSoup
r = requests.get('https://www.faceit.com/en/csgo/room/1-8d6729b5-cfeb-4059-8894-3b07e04e76b2')
soup = BeautifulSoup(r.content, 'html.parser')
extracted_link = soup.find_all('href', class_='list-unstyled')
print(extracted_link)
Example Link : https://www.faceit.com/en/csgo/room/1-8d6729b5-cfeb-4059-8894-3b07e04e76b2
Example Link Extracted : https://demos-europe-west2.faceit-cdn.net/csgo/f9eadb47-aea5-4672-9499-4f457c7d28bd.dem.gz
Example : https://paste.pics/AQBQY
All of the contents of the page is loaded dynamically, which means that BeautifulSoup won't see it. So you actually might be better off using selenium with a webdriver in headless mode.
For example:
import time
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
options = Options()
options.headless = True
driver = webdriver.Chrome(options=options)
url = "https://www.faceit.com/en/csgo/room/1-8d6729b5-cfeb-4059-8894-3b07e04e76b2"
driver.get(url)
time.sleep(2)
element = driver.find_element_by_css_selector('.match-vs .btn-default')
print(element.get_attribute("href"))
Output:
https://demos-europe-west2.faceit-cdn.net/csgo/f9eadb47-aea5-4672-9499-4f457c7d28bd.dem.gz
You can also do it using only requests:
import requests as r
room_id = '1-8d6729b5-cfeb-4059-8894-3b07e04e76b2'
link = 'https://api.faceit.com/match/v2/match/'+room_id
res = r.get(link)
data = res.json()
extracted_links = data['payload']['demoURLs']
print(extracted_links)
The code probes their API to get all the data at once as JSON, then just extract the needed information.
i am tring to extract text inside span-id tag but getting blank output screen.
i have tried using parent element div text also , but fail to extract, please anyone help me.
below is my code.
import requests
from bs4 import BeautifulSoup
r = requests.get('https://www.paperplatemakingmachines.com/')
soup = BeautifulSoup(r.text,'lxml')
mob = soup.find('span',{"id":"tollfree"})
print(mob.text)
i want the text inside that span which is given mobile number.
You'll have to use Selenium as that text is not present in the initial request, or at least no without searching through <script> tags.
from bs4 import BeautifulSoup as soup
from selenium import webdriver
import time
driver = webdriver.Chrome('C:\chromedriver_win32\chromedriver.exe')
url='https://www.paperplatemakingmachines.com/'
driver.get(url)
# It's better to use Selenium's WebDriverWait, but I'm still learning how to use that correctly
time.sleep(5)
soup = BeautifulSoup(driver.page_source, 'html.parser')
driver.close()
mob = soup.find('span',{"id":"tollfree"})
print(mob.text)
The Data is actually rending dynamically through script. What you need to do is parse the data from script:
import requests
import re
from bs4 import BeautifulSoup
r = requests.get('https://www.paperplatemakingmachines.com/')
soup = BeautifulSoup(r.text,'lxml')
script= soup.find('script')
mob = re.search("(?<=pns_no = \")(.*)(?=\";)", script.text).group()
print(mob)
Another way of using regex to find the number
import requests
import re
from bs4 import BeautifulSoup as bs
r = requests.get('https://www.paperplatemakingmachines.com/',)
soup = bs(r.content, 'lxml')
r = re.compile(r'var pns_no = "(\d+)"')
data = soup.find('script', text=r).text
script = r.findall(data)[0]
print('+91-' + script)
import time
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from bs4 import BeautifulSoup
from urllib.request import Request, urlopen
import re
import pandas as pd
from pytube import YouTube
browser = webdriver.Chrome("C:/Users/Downloads/chromedriver_win32/chromedriver.exe")
browser.get("https://www.youtube.com/channel/UCaKt8dvEIPnEHWSbLYhzrxg/videos")
time.sleep(1)
elem = browser.find_element_by_tag_name("body")
no_of_pagedowns = 100
while no_of_pagedowns:
elem.send_keys(Keys.PAGE_DOWN)
time.sleep(0.2)
no_of_pagedowns-=1
html = browser.page_source
soup = BeautifulSoup(html, "lxml")
tags = soup.find_all('a')
fname = "C:/Stock_in_CFD/Output.txt"
text_file = open(fname, "w+", encoding="utf-8")
for tag in tags:
t = tag.get('href')
text_file.write(t)
When I am running the above code. I am getting error
TypeError: write() argument must be str, not None
When I am not using selenium I am able to do it.
I am using selenium since I want scroll down entire page before parsing before using BeautifulSoup