We Keep Coding

scraping sports data using requests or selenium - python

I am trying to scrape data from this page:
https://www.sofascore.com/betting-tips-today
I created this code but dont work:
import requests
url = "https://www.sofascore.com/betting-tips-today"
r = requests.get(url).json()
print(r)
I tried selenium, but don't work:
from bs4 import BeautifulSoup
import time
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
options = Options()
# options.add_argument("--headless") #headless
options.add_argument('--no-sandbox')
options.add_argument('--ignore-certificate-errors')
options.add_argument('--incognito')
driver = webdriver.Chrome(executable_path=r"C:/chromedriver.exe", options=options)
u = "https://www.sofascore.com/betting-tips-today"
driver.get(u)
WebDriverWait(driver, 20).until(EC.visibility_of_element_located((By.CSS_SELECTOR, "div[class^='Content__PageContainer-sc-']")))
time.sleep(20)
elem = driver.find_element_by_xpath("//*")
source_code = elem.get_attribute("innerHTML")
soup = BeautifulSoup(driver.page_source, 'html.parser')
# print(len(soup.find_all('h2')))
# print(len(soup.select('.ivqpwB')))
parent_soup = soup.find('h2', text=("Odds") ).parent.parent.select('div:nth-of-type(2) > div')
print(len(parent_soup))
for i in parent_soup:
print(i)
Any idea how I can scrape data inside this page ?

You could try like this:
import time
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
options = Options()
options.add_argument("--headless")
options.add_argument("--no-sandbox")
options.add_argument("--ignore-certificate-errors")
options.add_argument("--incognito")
driver = webdriver.Chrome(
executable_path=r"C:/chromedriver.exe", options=options
)
u = "https://www.sofascore.com/betting-tips-today"
driver.get(u)
# Get the page
WebDriverWait(driver, 20).until(
EC.visibility_of_element_located(
(By.CSS_SELECTOR, "div[class^='Content__PageContainer-sc-']")
)
)
time.sleep(20)
# Get the table
elem = driver.find_element_by_xpath(
'//*[#id="__next"]/main/div/div[2]/div/div[1]/div[2]/table'
)
source_code = elem.get_attribute("innerHTML")
# Parse the html
soup = BeautifulSoup(driver.page_source, "html.parser")
# Get the interesting data for each row
data = []
for row in soup.find_all("tr")[4:]:
infos = []
for item in row.find_all("td"):
for label in item.find_all("div"):
infos.append(label.text)
infos.append(item.text)
data.append(infos[3:5] + infos[13:14] + infos[16:17] + infos[20:])
print(data)
# Outputs
[['La Guaira', 'América Cali', '3.25', '3.20', '13.25X3.2022.25',
'1', '', '1', '31%', 'wins 57%'], ['Hapoel Holon', 'Burgos', '2.75',
'1.40', '1', '36%', 'wins 60%'] ...]
You now have a list (data) of lists (one list per row). You can make a dataframe of it with Pandas and do some more work.

Related

I have written a code that will run selenium using chromewebdriver. now i need to convert the code so that it will run msedgedriver. can someone send the code which is converted so that it will run on msedge driver and tell me how did they do it so that i can write the code the same way in future.
here is my code:
import time
import pandas as pd
from selenium import webdriver
from bs4 import BeautifulSoup
from selenium.webdriver.common.by import By
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.chrome.service import Service
from webdriver_manager.chrome import ChromeDriverManager
'''locators'''
bank_cost_lt=(By.XPATH,"//*[#id='itembox-InstantBankDiscount']//a")
x_mark_lt=(By.XPATH,"//*[#id='twister-plus-dp-bg']/i")
partner_lt=(By.XPATH,"//*[#id='itembox-Partner']//a[#class='a-size-base a-link-emphasis vsx-offers-count']")
options = webdriver.ChromeOptions()
prefs = {"profile.default_content_setting_values.notifications": 2}
options.add_experimental_option("prefs", prefs)
# driver=webdriver.Chrome(executable_path=chrome_exe_path, chrome_options=options)
driver = webdriver.Chrome(service=Service(ChromeDriverManager().install()), chrome_options=options)
driver.implicitly_wait(0.5)
# driver.maximize_window()
df=pd.DataFrame(columns=['url','price','seller','bank offers','partner offers'])
cnt=0
def presence_of_element_click(by_locator, timeout):
WebDriverWait(driver, timeout).until(EC.presence_of_element_located(by_locator)).click()
urls=["https://www.amazon.in/JBL-Cancellation-Headphones-Playtime-Assistant/dp/B096FYLJ6M/ref=sr_1_8?crid=OHZVHJG9Q7HN&keywords=jbl%2Bheadphones&qid=1672115942&s=electronics&sprefix=jbl%2Bheadphone%2Celectronics%2C235&sr=1-8&th=1"]
# urls = ["https://www.amazon.in/dp/B0BGZN7FWV?th=1"]
for url in urls:
print(url)
driver.get(url)
time.sleep(3)
WebDriverWait(driver, 180).until(lambda driver: driver.execute_script('return document.readyState') == 'complete')
elem = driver.find_element('xpath','//*')
source_code = elem.get_attribute("outerHTML")
soup1 = BeautifulSoup(source_code, "html.parser")
soup2 = BeautifulSoup(soup1.prettify(), "html.parser")
price = soup2.find('span',{'class':'a-price aok-align-center reinventPricePriceToPayMargin priceToPay'}).span.text
print(price)
seller=soup2.find('div',{'id':'merchant-info'}).find('a').find('span').text
print(seller)
presence_of_element_click(bank_cost_lt,60)
time.sleep(4)
bank_=driver.find_element('id','InstantBankDiscount-sideSheet')
source_code = bank_.get_attribute("outerHTML")
soup1 = BeautifulSoup(source_code, "html.parser")
soup2 = BeautifulSoup(soup1.prettify(), "html.parser")
bank_offer_els=soup2.find_all('div',{'class':'a-section vsx-offers-desktop-lv__item'})
lst=[]
for val in bank_offer_els:
lst.append(str(val.p.text).strip())
presence_of_element_click(x_mark_lt,60)
time.sleep(2)
presence_of_element_click(partner_lt,60)
time.sleep(2)
bank_=driver.find_element('id','Partner-single-offer')
source_code = bank_.get_attribute("outerHTML")
soup1 = BeautifulSoup(source_code, "html.parser")
soup2 = BeautifulSoup(soup1.prettify(), "html.parser")
partner_els=soup2.find_all('div',{'class':'a-section vsx-offers-desktop-dv__content aok-block'})
par_lst=[]
for val in partner_els:
par_lst.append(str(val.text).strip())
presence_of_element_click(x_mark_lt,60)
df.loc[cnt,'url']=url
df.loc[cnt,'price']=price.strip()
df.loc[cnt,'seller']= seller.strip()
if lst:
df.loc[cnt,'bank offers']=', '.join(lst)
else:
df.loc[cnt,'bank offers']='No offers'
if par_lst:
df.loc[cnt,'partner offers']=', '.join(par_lst)
else:
df.loc[cnt,'partner offers']='No Offers'
cnt+=1
df.to_excel('output1.xlsx',index=False)

If you're using Selenium 4, you only need to change Chrome related code to Edge related. The edited lines of code are below:
from selenium.webdriver.edge.service import Service
from webdriver_manager.microsoft import EdgeChromiumDriverManager
options = webdriver.EdgeOptions()
driver = webdriver.Edge(service=Service(EdgeChromiumDriverManager().install()), options=options)
If you want to learn more about Edge WebDriver automation, you can refer to this doc: Use WebDriver to automate Microsoft Edge.

I got a dataframe that contains links to google reviews of two restaurants. I wanted to load all reviews of two restaurants (one by one) into the browser and then save them into a new data frame. I wrote a script that reads and load all reviews into the browser as follow:
from selenium import webdriver
import pandas as pd
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.action_chains import ActionChains
import time
link_df = Link
0 https://www.google.com/search?q=restaurant+in+christchurch&biw=1280&bih=614&hotel_occupancy=2&tbm=lcl&sxsrf=AOaemvI4qlEAr3btedb6PCx9U53RtXkI2Q%3A1635630947742&ei=Y799YaHfLOKZ4-EPoeqjmA4&oq=restaurant+in+christchurch&gs_l=psy-ab.3...0.0.0.614264.0.0.0.0.0.0.0.0..0.0....0...1c..64.psy-ab..0.0.0....0.7jAOI05vCjI#lrd=0x6d318a3aa3041455:0x5f83f4fae76d8656,1,,,&rlfi=hd:;si:6882614014013965910,l,ChpyZXN0YXVyYW50IGluIGNocmlzdGNodXJjaEiglZKhm6qAgAhaKBAAGAAYAiIacmVzdGF1cmFudCBpbiBjaHJpc3RjaHVyY2gqBAgDEACSARJidXJtZXNlX3Jlc3RhdXJhbnSqAQwQASoIIgRmb29kKAA,y,UB2auy7TMYs;mv:[[-43.4870861,172.6509735],[-43.5490232,172.5976049]]
1 https://www.google.com/search?q=restaurant+in+christchurch&biw=1280&bih=614&hotel_occupancy=2&tbm=lcl&sxsrf=AOaemvI4qlEAr3btedb6PCx9U53RtXkI2Q%3A1635630947742&ei=Y799YaHfLOKZ4-EPoeqjmA4&oq=restaurant+in+christchurch&gs_l=psy-ab.3...0.0.0.614264.0.0.0.0.0.0.0.0..0.0....0...1c..64.psy-ab..0.0.0....0.7jAOI05vCjI#lrd=0x6d318bf82139caaf:0xf115cd7fe794cbcc,1,,,&rlfi=hd:;si:17372017086881385420,l,ChpyZXN0YXVyYW50IGluIGNocmlzdGNodXJjaEjh9auu-q6AgAhaKBAAGAAYAiIacmVzdGF1cmFudCBpbiBjaHJpc3RjaHVyY2gqBAgDEACSAQpyZXN0YXVyYW50qgEMEAEqCCIEZm9vZCgA,y,ZeJbBWd7wDg;mv:[[-43.4870861,172.6509735],[-43.5490232,172.5976049]]
i = 0
driver = webdriver.Chrome()
for index, i in link_df.iterrows():
base_url = i['Link'] #link_df['Link'][i]
driver.get(base_url)
WebDriverWait(driver,10).until(EC.element_to_be_clickable((By.XPATH,"//div[./span[text()='Newest']]"))).click()
print('Restaurant number is ',index)
title = driver.find_element_by_xpath("//div[#class='P5Bobd']").text
address = driver.find_element_by_xpath("//div[#class='T6pBCe']").text
overall_rating = driver.find_element_by_xpath("//div[#class='review-score-container']//span[#class='Aq14fc']").text
total_reviews_text =driver.find_element_by_xpath("//div[#class='review-score-container']//div//div//span//span[#class='z5jxId']").text
num_reviews = int (total_reviews_text.split()[0])
all_reviews = WebDriverWait(driver, 20).until(EC.presence_of_all_elements_located((By.CSS_SELECTOR, 'div.gws-localreviews__google-review')))
time.sleep(2)
total_reviews = len(all_reviews)
while total_reviews < num_reviews:
driver.execute_script('arguments[0].scrollIntoView(true);', all_reviews[-1])
WebDriverWait(driver, 5, 0.25).until_not(EC.presence_of_element_located((By.CSS_SELECTOR, 'div[class$="activityIndicator"]')))
time.sleep(5)
all_reviews = WebDriverWait(driver, 5).until(EC.presence_of_all_elements_located((By.CSS_SELECTOR, 'div.gws-localreviews__google-review')))
print(total_reviews)
total_reviews +=1
reviews_info = driver.find_elements_by_xpath("//div[#class='jxjCjc']")
review_information = pd.DataFrame(columns=["Restaurant title","Restaurant rating","Total reviews","Reviewer Name","Rating", "Review"])
name= ''
rating = ''
text = ''
for index,review_info in enumerate(reviews_info):
name = review_info.find_element_by_xpath("./div/div/a").text
rating = review_info.find_element_by_xpath(".//div[#class='PuaHbe']//g-review-stars//span").get_attribute('aria-label')
text = review_info.find_element_by_xpath(".//div[#class='Jtu6Td']//span").text
review_information.at[len(review_information)] = [title,overall_rating,num_reviews,name,rating,text]
filename = 'Google_reviews' + ' ' +pd.to_datetime("now").strftime("%Y_%m_%d")+'.csv'
files_present = glob.glob(filename)
if files_present:
review_information.to_csv(filename,index=False,mode='a',header=False)
else:
review_information.to_csv(filename,index=False)
driver.get('https:ww.google.com')
time.sleep(3)
The problem is that script throws an error when it reaches the following line.
driver.execute_script('arguments[0].scrollIntoView(true);', all_reviews[-1])
It throws following error:
StaleElementReferenceException: Message: stale element reference: element is not attached to the page document
(Session info: chrome=95.0.4638.69)
When I tried the same program without storing google links in dataframe (i.e. no for loop and instead of base_url = i['Link'], I wrote base_url = google review link) it works fine.
I am not sure where I am making the mistake. Any suggestion or help to fix the issue would be highly appreciated?

EDIT
you put the creation of driver outside the for loop
you cant launch the new url with gps data when the first popup is always in front, if you launch it, it stays in backdoor, the easier way is to launch a new url without gps data -> https:ww.google.com and wait 3 dec before to follow your loop:
your count is not good, i have changed your selector and change the total and set some lines in comment
from selenium import webdriver
import pandas as pd
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.action_chains import ActionChains
from selenium.webdriver.firefox.options import Options
import time
link_df = ["https://www.google.com/search?q=restaurant+in+christchurch&biw=1280&bih=614&hotel_occupancy=2&tbm=lcl&sxsrf=AOaemvI4qlEAr3btedb6PCx9U53RtXkI2Q%3A1635630947742&ei=Y799YaHfLOKZ4-EPoeqjmA4&oq=restaurant+in+christchurch&gs_l=psy-ab.3...0.0.0.614264.0.0.0.0.0.0.0.0..0.0....0...1c..64.psy-ab..0.0.0....0.7jAOI05vCjI#lrd=0x6d318a3aa3041455:0x5f83f4fae76d8656,1,,,&rlfi=hd:;si:6882614014013965910,l,ChpyZXN0YXVyYW50IGluIGNocmlzdGNodXJjaEiglZKhm6qAgAhaKBAAGAAYAiIacmVzdGF1cmFudCBpbiBjaHJpc3RjaHVyY2gqBAgDEACSARJidXJtZXNlX3Jlc3RhdXJhbnSqAQwQASoIIgRmb29kKAA,y,UB2auy7TMYs;mv:[[-43.4870861,172.6509735],[-43.5490232,172.5976049]]",
"https://www.google.com/search?q=restaurant+in+christchurch&biw=1280&bih=614&hotel_occupancy=2&tbm=lcl&sxsrf=AOaemvI4qlEAr3btedb6PCx9U53RtXkI2Q%3A1635630947742&ei=Y799YaHfLOKZ4-EPoeqjmA4&oq=restaurant+in+christchurch&gs_l=psy-ab.3...0.0.0.614264.0.0.0.0.0.0.0.0..0.0....0...1c..64.psy-ab..0.0.0....0.7jAOI05vCjI#lrd=0x6d318bf82139caaf:0xf115cd7fe794cbcc,1,,,&rlfi=hd:;si:17372017086881385420,l,ChpyZXN0YXVyYW50IGluIGNocmlzdGNodXJjaEjh9auu-q6AgAhaKBAAGAAYAiIacmVzdGF1cmFudCBpbiBjaHJpc3RjaHVyY2gqBAgDEACSAQpyZXN0YXVyYW50qgEMEAEqCCIEZm9vZCgA,y,ZeJbBWd7wDg;mv:[[-43.4870861,172.6509735],[-43.5490232,172.5976049]]"
]
i = 0
binary = r'C:\Program Files (x86)\Mozilla Firefox\firefox.exe'
cap = DesiredCapabilities().FIREFOX
cap["marionette"] = True
options = Options()
options.binary = binary
driver = webdriver.Firefox(options=options, capabilities=cap, executable_path="E:\\Téléchargement\\geckodriver.exe")
# i have to launch one time to accept the cookies manually
#by setting a breakpoint after, but you dont have that i think
#driver.get(link_df[0])
print ("Headless Firefox Initialized")
print(link_df)
for url in link_df:
base_url = url # i['Link'] # link_df['Link'][i]
print(base_url)
driver.get(base_url)
WebDriverWait(driver, 10).until(EC.element_to_be_clickable((By.XPATH, "//div[./span[text()='Avis les plus récents']]"))).click()
title = driver.find_element_by_xpath("//div[#class='P5Bobd']").text
address = driver.find_element_by_xpath("//div[#class='T6pBCe']").text
overall_rating = driver.find_element_by_xpath("//div[#class='review-score-container']//span[#class='Aq14fc']").text
total_reviews_text = driver.find_element_by_xpath(
"//div[#class='review-score-container']//div//div//span//span[#class='z5jxId']").text
num_reviews = int(total_reviews_text.split()[0])
all_reviews = WebDriverWait(driver, 20).until(EC.presence_of_all_elements_located((By.CSS_SELECTOR, '#reviewSort .gws-localreviews__google-review')))
# time.sleep(2)
total_reviews = 0
while total_reviews < num_reviews:
driver.execute_script('arguments[0].scrollIntoView(true);', all_reviews[-1])
WebDriverWait(driver, 5, 0.25).until_not(EC.presence_of_element_located((By.CSS_SELECTOR, 'div[class$="activityIndicator"]')))
all_reviews = WebDriverWait(driver, 5).until(
EC.presence_of_all_elements_located((By.CSS_SELECTOR, '#reviewSort .gws-localreviews__google-review')))
total_reviews = len(all_reviews)
print(total_reviews, len(all_reviews))
driver.get('https:ww.google.com') # or driver.close() if no bugs
time.sleep(3)
driver.close()
driver.quit()
it seems the solution for chrome needs some fixes:
org.openqa.selenium.StaleElementReferenceException: stale element reference: element is not attached to the page document
The literal meaning is about , The referenced element is out of date , No longer attached to the current page . Usually , This is because the page has been refreshed or skipped , The solution is , Reuse findElement or findElements Method to locate the element .
so its seems for chrome there is a problem of refreshing, so i suggest to load the number of record before to scroll, to have a fresh copy of DOM items, and i have to add a wait 1sec at the end of while loop
from selenium import webdriver
import pandas as pd
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.action_chains import ActionChains
#from selenium.webdriver.firefox.options import Options
from selenium.webdriver.chrome.options import Options
import time
link_df = [
"https://www.google.com/search?q=restaurant+in+christchurch&biw=1280&bih=614&hotel_occupancy=2&tbm=lcl&sxsrf=AOaemvI4qlEAr3btedb6PCx9U53RtXkI2Q%3A1635630947742&ei=Y799YaHfLOKZ4-EPoeqjmA4&oq=restaurant+in+christchurch&gs_l=psy-ab.3...0.0.0.614264.0.0.0.0.0.0.0.0..0.0....0...1c..64.psy-ab..0.0.0....0.7jAOI05vCjI#lrd=0x6d318a3aa3041455:0x5f83f4fae76d8656,1,,,&rlfi=hd:;si:6882614014013965910,l,ChpyZXN0YXVyYW50IGluIGNocmlzdGNodXJjaEiglZKhm6qAgAhaKBAAGAAYAiIacmVzdGF1cmFudCBpbiBjaHJpc3RjaHVyY2gqBAgDEACSARJidXJtZXNlX3Jlc3RhdXJhbnSqAQwQASoIIgRmb29kKAA,y,UB2auy7TMYs;mv:[[-43.4870861,172.6509735],[-43.5490232,172.5976049]]",
"https://www.google.com/search?q=restaurant+in+christchurch&biw=1280&bih=614&hotel_occupancy=2&tbm=lcl&sxsrf=AOaemvI4qlEAr3btedb6PCx9U53RtXkI2Q%3A1635630947742&ei=Y799YaHfLOKZ4-EPoeqjmA4&oq=restaurant+in+christchurch&gs_l=psy-ab.3...0.0.0.614264.0.0.0.0.0.0.0.0..0.0....0...1c..64.psy-ab..0.0.0....0.7jAOI05vCjI#lrd=0x6d318bf82139caaf:0xf115cd7fe794cbcc,1,,,&rlfi=hd:;si:17372017086881385420,l,ChpyZXN0YXVyYW50IGluIGNocmlzdGNodXJjaEjh9auu-q6AgAhaKBAAGAAYAiIacmVzdGF1cmFudCBpbiBjaHJpc3RjaHVyY2gqBAgDEACSAQpyZXN0YXVyYW50qgEMEAEqCCIEZm9vZCgA,y,ZeJbBWd7wDg;mv:[[-43.4870861,172.6509735],[-43.5490232,172.5976049]]"
]
i = 0
binaryfirefox = r'C:\Program Files (x86)\Mozilla Firefox\firefox.exe'
binarychrome = r'C:\Program Files (x86)\Google\Chrome\Application\chrome.exe'
options = Options()
#cap = DesiredCapabilities().CHROME
#cap["marionette"] = True
#cap = DesiredCapabilities().FIREFOX
#options.binary = binaryfirefox
#driver = webdriver.Firefox(options=options, capabilities=cap, executable_path="E:\\Téléchargement\\geckodriver.exe")
options.binary_location = binarychrome
driver = webdriver.Chrome(options=options, executable_path="E:\\Téléchargement\\chromedriver.exe" )
# same reason tha Firefox i have to load one time
# an url to accept manually the cookies
#driver.get(link_df[0])
print(link_df)
for url in link_df:
base_url = url # i['Link'] # link_df['Link'][i]
print(base_url)
driver.get(base_url)
WebDriverWait(driver, 10).until(EC.element_to_be_clickable((By.XPATH, "//div[./span[text()='Newest']]"))).click()
title = driver.find_element_by_xpath("//div[#class='P5Bobd']").text
address = driver.find_element_by_xpath("//div[#class='T6pBCe']").text
overall_rating = driver.find_element_by_xpath("//div[#class='review-score-container']//span[#class='Aq14fc']").text
total_reviews_text = driver.find_element_by_xpath(
"//div[#class='review-score-container']//div//div//span//span[#class='z5jxId']").text
num_reviews = int(total_reviews_text.split()[0])
all_reviews = WebDriverWait(driver, 20).until(EC.presence_of_all_elements_located((By.CSS_SELECTOR, '#reviewSort .gws-localreviews__google-review')))
# time.sleep(2)
total_reviews = 0
while total_reviews < num_reviews:
#reload to avoid exception, or trap scroll with try/except but more expznsive
all_reviews = WebDriverWait(driver, 20).until(
EC.presence_of_all_elements_located((By.CSS_SELECTOR, '#reviewSort .gws-localreviews__google-review')))
driver.execute_script('arguments[0].scrollIntoView(true);', all_reviews[-1])
total_reviews = len(all_reviews)
print(total_reviews, len(all_reviews))
time.sleep(1)
driver.get('https:ww.google.com') # or driver.close() if no bugs
time.sleep(3)
driver.close()
driver.quit()

I want to scrape data inside nested tables, in this page: https://www.wagertalk.com/freeOddsPage/page.html?sport=L5&date=2021-05-29&cb=0.01844398326591401
When you click on any cell, a nested new table appears, I want to scrape data from those nested tables.
I created a phyton script trying to use selenium to click on each cell then the table show so I scrape it; but the elenium browser didn't click or the nested tables didn't show:
u = 'https://www.wagertalk.com/freeOddsPage/page.html?sport=S8&date=2021-05-27&cb=0.6242232189793953'
import requests
import csv
import json
import datetime
from bs4 import BeautifulSoup
import time
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
options = Options()
# options.add_argument("--headless") #headless
#options.add_argument('--no-sandbox')
#options.add_argument('--ignore-certificate-errors')
#options.add_argument('--incognito')
driver = webdriver.Chrome(executable_path=r"C:/chromedriver.exe", options=options)
driver.get(u)
driver.maximize_window()
driver.implicitly_wait(60) ##Wait the loading if error
time.sleep(20)
soup = BeautifulSoup(driver.page_source, 'html.parser')
soup = BeautifulSoup(driver.page_source, 'html.parser')
for i in soup.select('#schedule tbody tr[id^="g"]:has(.tennis_score_main)'):
match_date = i.select_one('th:nth-of-type(1) div:nth-of-type(1)').text
match_time = i.select_one('th:nth-of-type(1) div:nth-of-type(2)').text
A_team = i.select_one('th:nth-of-type(3) div:nth-of-type(1) div:nth-of-type(1)').text if i.select_one('th:nth-of-type(3) div:nth-of-type(1) div:nth-of-type(1)') else i.select_one('th:nth-of-type(3) div:nth-of-type(1)').text
H_team = i.select_one('th:nth-of-type(3) div:nth-of-type(2) div:nth-of-type(1)').text if i.select_one('th:nth-of-type(3) div:nth-of-type(2) div:nth-of-type(1)') else i.select_one('th:nth-of-type(3) div:nth-of-type(2)').text
#I tried this:
# WebDriverWait(driver, 20).until(EC.element_to_be_clickable((By.CSS_SELECTOR,'#schedule tbody tr[id^="g"]:has(.scTD1):nth-of-type(1) .book.b10 div:nth-of-type(1)')))
#and Tried this:
driver.execute_script("document.querySelector('#schedule tbody tr:has(.scTD1):nth-of-type(1) .book.b10 div:nth-of-type(1)').click()")
#code to scrape nested table here, but the table don't show
driver.quit()

I don't know what was your problem because I can click cell to open popup window, and later click button Close to close this popup window. But I didn't use Beatifulsoup but only Selenium
I didn't check if it works with all cells and rows.
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
#from selenium.webdriver.firefox.options import Options
import time
url = 'https://www.wagertalk.com/freeOddsPage/page.html?sport=S8&date=2021-05-27&cb=0.6242232189793953'
options = Options()
#options.add_argument("--headless")
#options.add_argument('--no-sandbox')
#options.add_argument('--ignore-certificate-errors')
#options.add_argument('--incognito')
#driver = webdriver.Chrome(executable_path=r"C:/chromedriver.exe", options=options)
driver = webdriver.Chrome(options=options)
#driver = webdriver.Firefox(options=options)
driver.get(url)
driver.maximize_window()
driver.implicitly_wait(60)
for row in driver.find_elements_by_css_selector('tr[id^="g"]'):
date_time = row.find_elements_by_css_selector('.time-started')
match_date = date_time[0].text
match_time = date_time[1].text
print('date:', match_date, '| time:', match_time)
teams = row.find_elements_by_css_selector('.team div')
A_team = teams[0].text
H_team = teams[1].text
print('A_team:', A_team)
print('H_team:', H_team)
books = row.find_elements_by_css_selector('.book')
for b in books:
print('--- popup ---')
# open .popupDiv
b.click()
time.sleep(1)
# ... scrape table from .popupDiv ...
tds = driver.find_elements_by_css_selector('.popupDiv table td')
for t in tds:
print(t.text)
# close .popupDiv
driver.find_element_by_css_selector('.popupDiv button').click()
print('--- end row ---')
driver.quit()

I am a beginner in Python-Selenium scraping. I want to scrape permalink of all the Quora answers posted under a question. So far I have created the following code snippet. But when I run it, it gives me only one link in the output. This is due to the fact that the page isn't loaded fully I guess. What should I do to get at least 100 permalinks to answers from the page source?
from selenium import webdriver
from selenium.webdriver.common.by import
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException
driver_option = webdriver.ChromeOptions()
driver_option.add_argument(" — incognito")
chromedriver_path = './chromedriver'
def create_webdriver():
return webdriver.Chrome(executable_path=chromedriver_path, chrome_options=driver_option)
f = open('file_text.txt', 'w')
# Open the website
browser = create_webdriver()
browser.get("https://www.quora.com/How-do-I-prove-the-flat-earth-theory")
projects = browser.find_elements_by_xpath("//a[#class='answer_permalink']")
for proj in projects:
anslink = proj.get_attribute('href')
f.write(anslink)
f.close()

import requests
from bs4 import BeautifulSoup
r = requests.get("https://www.quora.com/How-do-I-prove-the-flat-earth-theory")
soup = BeautifulSoup(r.text, 'html.parser')
for item in soup.findAll("a", {'class': 'answer_permalink'}):
print(item.get("href"))
Output:
/How-do-I-prove-the-flat-earth-theory/answer/Dave-Morgan-14
/How-do-I-prove-the-flat-earth-theory/answer/Ken-Natco
/How-do-I-prove-the-flat-earth-theory/answer/Matthew-Writer
/How-do-I-prove-the-flat-earth-theory/answer/Chance-Thompson-13
/How-do-I-prove-the-flat-earth-theory/answers/27223260
/How-do-I-prove-the-flat-earth-theory/answers/26836797
/How-do-I-prove-the-flat-earth-theory/answer/Frida-Schiess
/How-do-I-prove-the-flat-earth-theory/answer/Pierre-Ripplinger
/How-do-I-prove-the-flat-earth-theory/answer/Jacob-Fu
/How-do-I-prove-the-flat-earth-theory/answer/Mike-Howells-4
/How-do-I-prove-the-flat-earth-theory/answer/Mick-Stute
/How-do-I-prove-the-flat-earth-theory/answer/Jesse-Bridges-III
/How-do-I-prove-the-flat-earth-theory/answer/Renard-Leblanc
/How-do-I-prove-the-flat-earth-theory/answers/26831140
/How-do-I-prove-the-flat-earth-theory/answers/27158717
/How-do-I-prove-the-flat-earth-theory/answer/Chris-Lockwood-4
/How-do-I-prove-the-flat-earth-theory/answer/David-Minger
/How-do-I-prove-the-flat-earth-theory/answer/Rick-Brown-50
/How-do-I-prove-the-flat-earth-theory/answer/Jacques-Malan-4
/How-do-I-prove-the-flat-earth-theory/answer/Robert-Lent-1
/How-do-I-prove-the-flat-earth-theory/answers/79419339
/How-do-I-prove-the-flat-earth-theory/answer/Dave-Consiglio
/How-do-I-prove-the-flat-earth-theory/answers/65113366
/How-do-I-prove-the-flat-earth-theory/answer/Krishnabh-Medhi
Selenium Approach:
from selenium import webdriver
from bs4 import BeautifulSoup
from selenium.webdriver.firefox.options import Options
from bs4 import BeautifulSoup
import time
options = Options()
options.add_argument('--headless')
driver = webdriver.Firefox(options=options)
driver.get(
'https://www.quora.com/How-do-I-prove-the-flat-earth-theory')
lenOfPage = driver.execute_script(
"window.scrollTo(0, document.body.scrollHeight);var lenOfPage=document.body.scrollHeight;return lenOfPage;")
match = False
while(match == False):
lastCount = lenOfPage
lenOfPage = driver.execute_script(
"window.scrollTo(0, document.body.scrollHeight);var lenOfPage=document.body.scrollHeight;return lenOfPage;")
if lastCount >= 51000:
break
soup = BeautifulSoup(driver.page_source, 'html.parser')
count = 0
for item in soup.findAll("a", {'class': 'answer_permalink'}):
count += 1
print(item.get("href"))
print(count)
driver.quit()
Output:
/How-do-I-prove-the-flat-earth-theory/answer/Dave-Morgan-14
/How-do-I-prove-the-flat-earth-theory/answer/Ken-Natco
/How-do-I-prove-the-flat-earth-theory/answer/Matthew-Writer
/How-do-I-prove-the-flat-earth-theory/answer/Chance-Thompson-13
/How-do-I-prove-the-flat-earth-theory/answers/27223260
/How-do-I-prove-the-flat-earth-theory/answers/26836797
/How-do-I-prove-the-flat-earth-theory/answer/Frida-Schiess
/How-do-I-prove-the-flat-earth-theory/answer/Pierre-Ripplinger
/How-do-I-prove-the-flat-earth-theory/answer/Jacob-Fu
/How-do-I-prove-the-flat-earth-theory/answer/Mike-Howells-4
/How-do-I-prove-the-flat-earth-theory/answer/Mick-Stute
/How-do-I-prove-the-flat-earth-theory/answer/Jesse-Bridges-III
/How-do-I-prove-the-flat-earth-theory/answer/Renard-Leblanc
/How-do-I-prove-the-flat-earth-theory/answers/26831140
/How-do-I-prove-the-flat-earth-theory/answer/Danya-Rose
/How-do-I-prove-the-flat-earth-theory/answer/Chris-Lockwood-4
/How-do-I-prove-the-flat-earth-theory/answer/David-Minger
/How-do-I-prove-the-flat-earth-theory/answer/Rick-Brown-50
/How-do-I-prove-the-flat-earth-theory/answer/Jacques-Malan-4
/How-do-I-prove-the-flat-earth-theory/answer/Robert-Lent-1
/How-do-I-prove-the-flat-earth-theory/answer/John-Lind-22
/How-do-I-prove-the-flat-earth-theory/answer/Dave-Consiglio
/How-do-I-prove-the-flat-earth-theory/answers/65113366
/How-do-I-prove-the-flat-earth-theory/answer/Krishnabh-Medhi
/How-do-I-prove-the-flat-earth-theory/answers/44569062
/How-do-I-prove-the-flat-earth-theory/answer/Abd-Ul-Rahman-Lomax
/How-do-I-prove-the-flat-earth-theory/answer/Helmut-Walle
/How-do-I-prove-the-flat-earth-theory/answer/Ed-Kohlwey-1
/How-do-I-prove-the-flat-earth-theory/answer/Jason-Ree-4
/How-do-I-prove-the-flat-earth-theory/answer/Drew-Curry
/How-do-I-prove-the-flat-earth-theory/answer/Darrel-Blakely-2
/How-do-I-prove-the-flat-earth-theory/answer/Alexander-Kunz-2
/How-do-I-prove-the-flat-earth-theory/answer/Michael-Greenberg-61
/How-do-I-prove-the-flat-earth-theory/answer/Matthew-Schenker
/How-do-I-prove-the-flat-earth-theory/answer/Gregory-Hart-8
/How-do-I-prove-the-flat-earth-theory/answer/Mark-Giammattei
/How-do-I-prove-the-flat-earth-theory/answer/Vernon-Bender
/How-do-I-prove-the-flat-earth-theory/answer/Brett-Evill
/How-do-I-prove-the-flat-earth-theory/answer/Kurt-Mager
/How-do-I-prove-the-flat-earth-theory/answer/Michael-Brenner-13
/How-do-I-prove-the-flat-earth-theory/answer/Luke-Anderson-87
/How-do-I-prove-the-flat-earth-theory/answer/Sassa-Neuf
/How-do-I-prove-the-flat-earth-theory/answer/Spandan-Mallick
/How-do-I-prove-the-flat-earth-theory/answers/58252346
/How-do-I-prove-the-flat-earth-theory/answer/Timothy-Lamothe
/How-do-I-prove-the-flat-earth-theory/answer/Eric-Schwertfeger
/How-do-I-prove-the-flat-earth-theory/answers/70843234
/How-do-I-prove-the-flat-earth-theory/answer/Tony-Flury
/How-do-I-prove-the-flat-earth-theory/answer/Aji-Jijo
/How-do-I-prove-the-flat-earth-theory/answer/Tia-Eastlake
/How-do-I-prove-the-flat-earth-theory/answer/Michael-Grace-53
/How-do-I-prove-the-flat-earth-theory/answer/Ray-Mason-30
/How-do-I-prove-the-flat-earth-theory/answer/Jimmy-May-2
/How-do-I-prove-the-flat-earth-theory/answer/Thomas-Edward-Samuel-Thomas
/How-do-I-prove-the-flat-earth-theory/answer/Alan-Atkinson-4
/How-do-I-prove-the-flat-earth-theory/answer/Joseph-Perkins-11
/How-do-I-prove-the-flat-earth-theory/answer/David-Ridlen
/How-do-I-prove-the-flat-earth-theory/answer/Charles-Li-86
/How-do-I-prove-the-flat-earth-theory/answers/140610748
/How-do-I-prove-the-flat-earth-theory/answer/Corentin-Oger
/How-do-I-prove-the-flat-earth-theory/answer/Jean-Pierre-Choisy
/How-do-I-prove-the-flat-earth-theory/answer/Tom-Kubin
/How-do-I-prove-the-flat-earth-theory/answers/120618033
/How-do-I-prove-the-flat-earth-theory/answer/Charles-Brenchley-1
/How-do-I-prove-the-flat-earth-theory/answer/Jonathan-Johnson-41
/How-do-I-prove-the-flat-earth-theory/answer/Edward-Teach-53
/How-do-I-prove-the-flat-earth-theory/answer/Tony-Price-50
/How-do-I-prove-the-flat-earth-theory/answer/Nathaniel-Day-8
/How-do-I-prove-the-flat-earth-theory/answer/Nuurussubchiy-Fikriy
/How-do-I-prove-the-flat-earth-theory/answers/150581075
/How-do-I-prove-the-flat-earth-theory/answers/87762707
/How-do-I-prove-the-flat-earth-theory/answer/Neil-219
/How-do-I-prove-the-flat-earth-theory/answer/Alex-Frantz-1
/How-do-I-prove-the-flat-earth-theory/answer/Andy-P-Zbinden
/How-do-I-prove-the-flat-earth-theory/answer/Uriel-Anderson-4
/How-do-I-prove-the-flat-earth-theory/answer/Chris-OLeary-19
/How-do-I-prove-the-flat-earth-theory/answer/Daniel-Gerber-7
/How-do-I-prove-the-flat-earth-theory/answer/Roy-Wilson-64
/How-do-I-prove-the-flat-earth-theory/answer/Randy-Wonsowicz-Jr
/How-do-I-prove-the-flat-earth-theory/answer/Leslie-Harrington-4
/How-do-I-prove-the-flat-earth-theory/answer/Eddie-Olsson
/How-do-I-prove-the-flat-earth-theory/answer/Vincent-Emery
/How-do-I-prove-the-flat-earth-theory/answer/Maxwell-Perry-3
/How-do-I-prove-the-flat-earth-theory/answer/Matthew-Granovsky
/How-do-I-prove-the-flat-earth-theory/answers/83259600
/How-do-I-prove-the-flat-earth-theory/answer/Benjamin-Dixon-17
/How-do-I-prove-the-flat-earth-theory/answer/John-Chambers-75
/How-do-I-prove-the-flat-earth-theory/answer/Ryne-Hanz
/How-do-I-prove-the-flat-earth-theory/answer/Eric-Rodriguez-137
/How-do-I-prove-the-flat-earth-theory/answer/Robert-Hopkins-90
/How-do-I-prove-the-flat-earth-theory/answer/Sasha-Maddah
/How-do-I-prove-the-flat-earth-theory/answer/Owen-Lee-126
/How-do-I-prove-the-flat-earth-theory/answer/David-Phillips-133
/How-do-I-prove-the-flat-earth-theory/answer/Hasan-Poonawala-1
/How-do-I-prove-the-flat-earth-theory/answer/Cristiano-Dal-Vi
/How-do-I-prove-the-flat-earth-theory/answer/Rex-Newborn
/How-do-I-prove-the-flat-earth-theory/answer/John-Neumann-9
/How-do-I-prove-the-flat-earth-theory/answer/Josh-D-Davis
/How-do-I-prove-the-flat-earth-theory/answer/Maruthi-Sreenath
/How-do-I-prove-the-flat-earth-theory/answer/Clint-Morgan-2
/How-do-I-prove-the-flat-earth-theory/answer/Nicholas-Volkmuth
/How-do-I-prove-the-flat-earth-theory/answer/Richard-Swim
/How-do-I-prove-the-flat-earth-theory/answers/143504277
/How-do-I-prove-the-flat-earth-theory/answer/Christer-Svanström
/How-do-I-prove-the-flat-earth-theory/answer/Steve-Schlackman-2
/How-do-I-prove-the-flat-earth-theory/answers/147597845
/How-do-I-prove-the-flat-earth-theory/answer/Rene-Dukundane-Felix
/How-do-I-prove-the-flat-earth-theory/answers/148753762
/How-do-I-prove-the-flat-earth-theory/answer/Henk-Schuring
/How-do-I-prove-the-flat-earth-theory/answers/135814117
/How-do-I-prove-the-flat-earth-theory/answer/Emilio-Trampuz
/How-do-I-prove-the-flat-earth-theory/answers/40529643
/How-do-I-prove-the-flat-earth-theory/answer/Karl-Sangree
/How-do-I-prove-the-flat-earth-theory/answer/Ted-Carriker
/How-do-I-prove-the-flat-earth-theory/answer/egi-syahban
/How-do-I-prove-the-flat-earth-theory/answer/Mayank-Dahiya-12
/How-do-I-prove-the-flat-earth-theory/answer/Robert-Jones-741
/How-do-I-prove-the-flat-earth-theory/answer/Jimmi-Carlsson-1
/How-do-I-prove-the-flat-earth-theory/answer/Cole-Johnson-24
/How-do-I-prove-the-flat-earth-theory/answer/Kram-Redarsh
/How-do-I-prove-the-flat-earth-theory/answers/64915389

My intention is to get the name, location, time of posting, title of the review and the whole review content from the web page (http://www.mouthshut.com/mobile-operators/Reliance-Jio-reviews-925812061).
My code :
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
firefox_capabilities = DesiredCapabilities.FIREFOX
firefox_capabilities['marionette'] = True
firefox_capabilities['binary'] = '/etc/firefox'
driver = webdriver.Firefox(capabilities=firefox_capabilities)
driver.get('http://www.mouthshut.com/mobile-operators/Reliance-Jio-reviews-925812061')
soup = BeautifulSoup(driver.page_source,"lxml")
for link in soup.select(".profile"):
try:
profile = link.select("p:nth-of-type(1) a")[0]
profile1 = link.select("p:nth-of-type(2)")[0]
except:pass
print(profile.text,profile1.text)
driver = webdriver.Firefox(capabilities=firefox_capabilities)
driver.get('http://www.mouthshut.com/mobile-operators/Reliance-Jio-reviews-925812061')
soup1 = BeautifulSoup(driver.page_source,"lxml")
for link in soup1.select(".col-10.review"):
try:
profile2 = link.select("small:nth-of-type(1)")[0]
profile3 = link.select("span:nth-of-type(3)")[0]
profile4 = link.select("a:nth-of-type(1)")[0]
except:pass
print(profile2.text,profile3.text,profile4.text)
driver = webdriver.Firefox(capabilities=firefox_capabilities)
driver.get('http://www.mouthshut.com/mobile-operators/Reliance-Jio-reviews-925812061')
soup2 = BeautifulSoup(driver.page_source,"lxml")
for link in soup2.select(".more.review"):
try:
containers=page_soup.findAll("div",{"class":"more reviewdata"})
count=len(containers)
for index in range(count):
count1=len(containers[index].p)
for i in range(count1):
profile5 = link.select("p:nth-of-type(i)")[0]
except:pass
print(profile5.text)
driver.quit()
I am getting the output for name, location, time and title of the review but I am unable to get the full review of a user. I would be grateful, if anyone could help me in getting the output for the same, along with the optimization of my code (i.e) I want my code to extract the required data by loading the web page only once. Also, It would be very helpful for me if someone could help me in extracting all the customer reviews of Jio from all the webpages of the website.

You can achieve the same with few lines of code along with lesser pain. However, I've defined here three main categories, as in name, review_title, review_data and the rest of the fields you can twitch very easily.
This is how you can do alternatively:
from selenium import webdriver;import time
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
driver = webdriver.Chrome()
driver.get("http://www.mouthshut.com/mobile-operators/Reliance-Jio-reviews-925812061")
wait = WebDriverWait(driver, 10)
for item in wait.until(EC.presence_of_all_elements_located((By.CSS_SELECTOR, ".review-article"))):
link = item.find_element_by_css_selector(".reviewdata a")
link.click()
time.sleep(2)
name = item.find_element_by_css_selector("p a").text
review_title = item.find_element_by_css_selector("strong a[id^=ctl00_ctl00_ContentPlaceHolderFooter_ContentPlaceHolderBody_rptreviews]").text
review_data = ' '.join([' '.join(items.text.split()) for items in item.find_elements_by_css_selector(".reviewdata")])
print("Name: {}\nReview_Title: {}\nReview_Data: {}\n".format(name, review_title, review_data))
driver.quit()
Or to do the same combinedly (selenium + bs4):
from bs4 import BeautifulSoup
from selenium import webdriver;import time
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
driver = webdriver.Chrome()
driver.get("http://www.mouthshut.com/mobile-operators/Reliance-Jio-reviews-925812061")
wait = WebDriverWait(driver, 10)
for items in wait.until(EC.presence_of_all_elements_located((By.CSS_SELECTOR, ".review-article"))):
link = items.find_element_by_css_selector(".reviewdata a")
link.click()
time.sleep(2)
soup = BeautifulSoup(driver.page_source,"lxml")
for item in soup.select(".review-article"):
name = item.select("p a")[0].text
review_title = item.select("strong a[id^=ctl00_ctl00_ContentPlaceHolderFooter_ContentPlaceHolderBody_rptreviews]")[0].text
review_data = ' '.join([' '.join(items.text.split()) for items in item.select(".reviewdata")])
print("Name: {}\nReview_Title: {}\nReview_Data: {}\n".format(name, review_title, review_data))
driver.quit()