討論 » 開發

scraping problems through popup windows

§
發表於:2020-08-06

Hello everyone, I can not srapen the pages because a pop up window is displayed immediately.
I need help or tips from you on how I can confirm the pop up more firmly in the code.

my python code:

import requests
from bs4 import BeautifulSoup
import csv
import pandas as pd
from time import sleep
from selenium import webdriver
from webdriver_manager.chrome import ChromeDriverManager
from selenium.webdriver.common.keys import Keys


def connect():
try:
requests.get('http://google.com') #Python 3.x
return True
except:
return False
def gernate_file():
headers_text = []
headers_text.append('Article Number')
headers_text.append('Title')
headers_text.append('Amount')
headers_text.append('Weight')
headers_text.append('Price')
headers_text.append('Categorie')
headers_text.append('Link')
headers_text.append('Image Url')
headers_text.append('Article Number')

df = pd.DataFrame([], columns=headers_text)
df.to_csv('Results.csv', index=False, encoding='utf-8-sig')
def hasNumbers(inputString):
return any(char.isdigit() for char in inputString)
# url='https://www.docmorris.de/optifast-drink-kaffee/10267833'
# url='https://www.docmorris.de/orlistat-hexal-60-mg/08982497'
def profileScraper(url,index):
while(not connect()):
print('no internet')
sleep(5)
res= requests.get(url)
driver = webdriver.Chrome(ChromeDriverManager().install())
driver.get(url)
soup=BeautifulSoup(res.content,features='html.parser')


title=soup.find('h1',class_='element-name')
if title is not None:
title=title.text.strip()
else:
return 0
print(title)




Weight=soup.find('dd',class_='col-8')
if Weight is not None:
Weight=Weight.text.strip()
else:
Weight='N/A'
print(Weight)




Price=soup.find('span',class_='price')
if Price is not None:
Price = Price.text.strip()
else:
Price='N/A'
print(Price)



Categories=soup.find_all('dd',href_='col-8 ')
if Categories is not None:
Categories = Categories.text.strip()
else:
Categories='N/A'
print(Categories)


amount=title.split('Stück')[0]
amountSplit=title.split('Stück')[0].split(' ')
for split in amountSplit:
if hasNumbers(split):
amount=split
if not hasNumbers(amount):


amount=soup.find('button',class_='btn-sm')
if amount is not None:
print(amount.text.split(':')[1].split('x')[0].strip())
amount=amount.text.split(':')[1].split('x')[0].strip()
else:
amount='1 Pack'
print(amount)


sleep(2)
img_url_text = 'N/D'
try:
img_url_text = driver.find_element_by_xpath("//figure[@class ='gallery-slider__item']").get_attribute('src')
driver.close()
finally:
print(img_url_text)


art_tags=article_no_tags.find('dd',class_='col-8')
if art_tags is not None:
article_no=art_tags.text.strip()
print(article_no)

return[index,title,'`'+amount,Weight,Price,Categories,url,img_url_text,article_no]

with open('test.csv', 'r', encoding='utf-8') as readFile:
reader = csv.reader(readFile)
file_lines = list(reader)

# print(file_lines[1][6])
gernate_file()
for index, row in enumerate(file_lines[1:]):
print(index)
# print(row[6])
record=[]
record = profileScraper(row[6],index+1)
df = pd.DataFrame([record])
df.to_csv('Results.csv', index=False, mode='a', encoding='utf-8-sig', header=False)
# break
print()
print(record)


Thanks in advance

§
發表於:2020-08-06

the screenshot

發表回覆

登入以回復