Advertisement
Malic

task1

Aug 31st, 2019
307
0
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 2.87 KB | None | 0 0
  1. def headers_parser(headers_string):
  2. headers_split=headers_string.split('\n')
  3. headers={}
  4. for header in headers_split:
  5. headers[header.split(': ')[0]]=header.split(': ')[1]
  6. return headers
  7.  
  8. import requests
  9. from bs4 import BeautifulSoup
  10.  
  11. headers='''{Host: www.linkedin.com
  12. User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:68.0) Gecko/20100101 Firefox/68.0
  13. Accept: application/vnd.linkedin.normalized+json+2.1
  14. Accept-Language: en-US,en;q=0.5
  15. Accept-Encoding: gzip, deflate, br
  16. x-li-lang: en_US
  17. x-li-track: {"clientVersion":"1.5.*","osName":"web","timezoneOffset":3,"deviceFormFactor":"DESKTOP","mpName":"voyager-web"}
  18. x-li-page-instance: urn:li:page:d_flagship3_search_srp_top;fneKWn18TgShV4N9JX4iRQ==
  19. csrf-token: ajax:0013840124082047075
  20. x-restli-protocol-version: 2.0.0
  21. Connection: keep-alive
  22. Referer: https://www.linkedin.com/search/results/all/?keywords=cisco&origin=GLOBAL_SEARCH_HEADER
  23. Cookie: bcookie="v=2&2792f1f4-894d-4ee1-825c-933e88f2f349"; bscookie="v=1&20190826104741d1cbea64-ac9f-417a-8dad-41f931b6b14dAQFA7v1fVQy1qgM4bwA0gPCMjscpTL1b"; _ga=GA1.2.1056146498.1566816461; lidc="b=TB96:g=1748:u=17:i=1567268736:t=1567329568:s=AQHCY6xtYlznzHf0qxwmzOcP1al04cCX"; AMCV_14215E3D5995C57C0A495C55%40AdobeOrg=-1303530583%7CMCIDTS%7C18139%7CMCMID%7C70401722693306760231315295735047971860%7CMCAAMLH-1567869575%7C9%7CMCAAMB-1567869575%7C6G1ynYcLPuiQxYZrsz_pkqfLG9yMXBpb2zX5dvJdYQJzPXImdj0y%7CMCOPTOUT-1567271975s%7CNONE%7CvVersion%7C3.3.0%7CMCCIDH%7C696003597; AMCVS_14215E3D5995C57C0A495C55%40AdobeOrg=1; liap=true; sl=v=1&FbOKp; li_at=AQEDARszUPgBENq3AAABbOF6qGsAAAFtBYcsa00AdcocN5T-uRR00gDJBmjDraBKLc7V5OYsdF_k4ps__kSc1Xrq7eUG5EhgaPTeouDb6zFb2xV4u8bWdEx0vKLwTxgjAl6GqRCdsl5G-IcGIX5ktHPS; JSESSIONID="ajax:0013840124082047075"; lissc1=1; lissc2=1; lang=v=2&lang=en-us; _lipt=CwEAAAFs58Bf3-Eozpn28T9QAvmgoMqgL0myVlY-3aIMzH5MKmGksZmaT4P9ilMNRYpqqHoS1Mwp7AEDl3NRz-Lb6uHKCvK8J2OWKPqq8lTDCkSgA83GgHp9VWE3vSflejc3e2pwiwx3Obnx8mg2XlzOeDgiArYXTTFNfF4zdLIqads; sdsc=1%3A1SZM1shxDNbLt36wZwCgPgvN58iw%3D; UserMatchHistory=AQIiYtUtmyLZbAAAAWzoST87eu9WjuP-L8v8uWNIFdcQDSWvf-gGw4HEuUerWywI3GtY-kLwoiEUIqnWhkO75aDuyJzH01f2W-zJ1QVIMp-1bhqkVgV27U0Frw5hPT83oS8v987FhoKgkrSvJMiYyXf9s0VeS4wYU6vBgb0uBg; aam_uuid=70246570412380188121337553404828587999; li_sugr=e3060b2e-9da4-431a-a4ee-9885529772e0; li_oatml=AQEwlNUcajMt7QAAAWzh4RD_3JtybHdi2LIP6a6Eyo3DNZ9whDzp2e9YM0as4fYfa7-L4JA3Tp0FVs5wkrh8BmVwy3X6NAKY; lil-lang=en_US
  24. TE: Trailers}'''
  25.  
  26.  
  27.  
  28. domain=input("please enter you domain ")
  29. params={'keywords':domain,'origin':'GLOBAL_SEARCH_HEADER','q':'blended'}
  30.  
  31. reqDomain=requests.get("https://www.linkedin.com/search/results/all/?keywords=cisco&origin=GLOBAL_SEARCH_HEADER",params=params,headers=headers).text
  32.  
  33. soupDomain=BeautifulSoup(reqDomain,"html.parser")
  34. print(soupDomain)
  35. #headerOption=soupDomain.findAll("h3",{"class":"search-result__title t-16 t-black t-bold"})
  36. #len(headerOption)
  37. #print(headerOption)
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement