从多个迭代页面返回数据

时间:2018-11-29 22:36:38

标签: python python-3.x loops web-scraping

以下代码从首页返回许可证。同样有1075页,如何从所有页面返回许可证号? [如果可能的话,我也想返回名称字段]

输入-我在网站的“ {Agent / Broker Last Name:”(代理商/经纪人的姓氏:)”字段中输入%号-http://mbsweblist.fsco.gov.on.ca/agents.aspx

这似乎是页码的操作-a href =“ javascript:__ doPostBack('ctl00 $ ctl00 $ MainPlaceHolder $ Content4 $ resultsGrid','Page $ 2')”> 2

谢谢,感谢您的帮助

import requests
from bs4 import BeautifulSoup

def get_result_page_ontario(name):
r = requests.post("http://mbsweblist.fsco.gov.on.ca/agents.aspx",
data={
    'ctl00$ctl00$MainPlaceHolder$Content4$bkmbname:': '%',
    '_EVENTTARGET': '',
    '__EVENTARGUMENT': '',
    '__LASTFOCUS': '',
    '__VIEWSTATE': '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',
    '__VIEWSTATEGENERATOR': '160FAD78',
    '__EVENTVALIDATION': '/wEdAA7Q4cvANrpN5o7qvL/AjrRj3ieM1gYOLXKttt+dfEvWRlC30MDmLdG0SqBLRp4Edr0smFtAlmZS0w2+VR/uBTUgaQpcj9uHtwyf+rB2XgM9KzV/VOD8+NmupvzRtXx7cILCclsqUAusKL6yu6LPJYCYN93eHCeJb+Wv6Dc0KUw/tN8+BEUTySkHJ91vQ/nzu4CsVp8wE0Bpab2MDGOxbDBR3HNdVeUhWlxmX6SwVRp9GtD5VgtZgtwF9KTW5gMitXmBcXMJkDk9iOnoeSz/z5VWv/AwskRm5Qo6YdBnxt7SdQEcL98iN0RCUjhr/FmBpke28iIjJEQtlWEoAG7jfIg+',
    'ctl00$ctl00$MainPlaceHolder$Content4$searchoption': 'Agents or Broker',
    'ctl00$ctl00$MainPlaceHolder$Content4$bkmbno': '',
    'ctl00$ctl00$MainPlaceHolder$Content4$bkmbname': name,
    'ctl00$ctl00$MainPlaceHolder$Content4$agbkcity': '',
    'ctl00$ctl00$MainPlaceHolder$Content4$srButton': 'Search',
    'ctl00$ctl00$hLocal': 'en',
    'ctl00$ctl00$hIsWide': '0'
})
return r.text

def parse_result_page_ontario(page):
soup = BeautifulSoup(page, 'html.parser')
allA = soup.find_all('a', href=True)
licenses = []
for a in allA:
    if('ShowLicence.aspx' in a['href']):
        licenses.append(a.text)
return licenses
name = '%'
page = get_result_page_ontario(name)
licenses = parse_result_page_ontario(page)
print (licenses)

0 个答案:

没有答案
相关问题