Created
October 26, 2019 22:56
-
-
Save salgo60/9b01ee10eecae54f277305f02d3cf1a1 to your computer and use it in GitHub Desktop.
webscraper
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import requests | |
| import urllib.request | |
| import time | |
| from bs4 import BeautifulSoup | |
| #url = 'https://www.alvin-portal.org/alvin/resultList.jsf?faces-redirect=true&searchType=PLACE&sortString=name_sort_asc&noOfRows=1000&af=%5B%5D&query=&aq=%5B%5B%7B"free_text"%3A"Turkiet"%7D%5D%5D&aqe=%5B%5D&dswid=-2660' | |
| urls =['https://www.alvin-portal.org/alvin/resultList.jsf?faces-redirect=true&includeViewParams=true&query=&searchType=PLACE&dswid=-2660&noOfRows=1000' | |
| ,'https://www.alvin-portal.org/alvin/resultList.jsf?dswid=-2660&p=1001&searchType=PLACE&sortString=name_sort_asc&noOfRows=1000&af=%5B%5D&query=&aq=%5B%5B%5D%5D&aqe=%5B%5D' | |
| ,'https://www.alvin-portal.org/alvin/resultList.jsf?dswid=-2660&p=2001&searchType=PLACE&sortString=name_sort_asc&noOfRows=1000&af=%5B%5D&query=&aq=%5B%5B%5D%5D&aqe=%5B%5D' | |
| ,'https://www.alvin-portal.org/alvin/resultList.jsf?dswid=-2660&p=3001&searchType=PLACE&sortString=name_sort_asc&noOfRows=1000&af=%5B%5D&query=&aq=%5B%5B%5D%5D&aqe=%5B%5D' | |
| ,'https://www.alvin-portal.org/alvin/resultList.jsf?dswid=-2660&p=4001&searchType=PLACE&sortString=name_sort_asc&noOfRows=1000&af=%5B%5D&query=&aq=%5B%5B%5D%5D&aqe=%5B%5D' | |
| ,'https://www.alvin-portal.org/alvin/resultList.jsf?dswid=-2660&p=5001&searchType=PLACE&sortString=name_sort_asc&noOfRows=1000&af=%5B%5D&query=&aq=%5B%5B%5D%5D&aqe=%5B%5D' | |
| ,'https://www.alvin-portal.org/alvin/resultList.jsf?dswid=-2660&p=6001&searchType=PLACE&sortString=name_sort_asc&noOfRows=1000&af=%5B%5D&query=&aq=%5B%5B%5D%5D&aqe=%5B%5D' | |
| ,'https://www.alvin-portal.org/alvin/resultList.jsf?dswid=-2660&p=7001&searchType=PLACE&sortString=name_sort_asc&noOfRows=1000&af=%5B%5D&query=&aq=%5B%5B%5D%5D&aqe=%5B%5D'] | |
| for url in urls: | |
| response = requests.get(url) | |
| soup = BeautifulSoup(response.text, "html.parser") | |
| soup.findAll('a') | |
| one_a_tag = soup.findAll('a')[36] | |
| link = one_a_tag['href'] | |
| time.sleep(1) | |
| for i in range(1,len(soup.findAll('a'))): | |
| one_a_tag = soup.findAll('a')[i] | |
| # print(one_a_tag) | |
| if "alvin-place" in one_a_tag['href']: | |
| print( one_a_tag.text,";",one_a_tag['href'].split('&')[6].replace("pid=","").replace("%3A",":")) | |
| #print( one_a_tag['href'].split('&')[6].replace("pid=","").replace("%3A",":")) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment