Python Crawl Weibo information

Sina Weibo crawl need to design to login, here I do not impersonate login, but use cookies to crawl.

To obtain a cookie:

650) this.width=650; "Src=" https://s1.51cto.com/wyfs02/M01/9D/F2/wKioL1mJML3j2zx3AADTqQSZXG0258.png-wh_500x0-wm_ 3-wmp_4-s_1312038099.png "title=" 05.png "alt=" Wkiol1mjml3j2zx3aadtqqszxg0258.png-wh_50 "/>

650) this.width=650; "Src=" https://s2.51cto.com/wyfs02/M01/9D/F2/wKiom1mJMNWR-NW3AAXbBOQBObw578.png-wh_500x0-wm_ 3-wmp_4-s_3181523793.png "title=" 04.png "alt=" Wkiom1mjmnwr-nw3aaxbboqbobw578.png-wh_50 "/>

Code:

#-*-coding:utf8-*-from bs4 import beautifulsoupimport requestsimport timeimport  Osimport sysimport randomreload (SYS)  sys.setdefaultencoding (' Utf-8 ') user_id =  User idcookie = {"Cookie":  "_t_wm=f3a2assae4335dfdf38fdc7a25a88; scf= Apmi3mluv9yh6ykz4i7-hmlhojzptqulc5g0xlrri-neo3xn1frwi5w1helzwg1bmkx4mv_ohkdtnv2ihxjqgls.;  SUB=_2A250jET_DeRhGeNN7FsX9CrIzzqIHXVXj2y3rDV6PUJbkdBeLUrnkW1AtfoOlrd_kyd1Izu7Q1uKaFvRDQ..;  suhb=0k1ysjsrjvbdgd; ssologinstate=1502098607 "}for page in range (:  )   url =  ' https://weibo.cn/573550093?page=%d '  % page     Response = requests.get (Url, cookies = cookie)     html =  response.text     soup = beautifulsoup (html,  ' lxml ')       username = soup.title.string    cttlisT = []    for ctt in  soup.find_all (' span ', class_= "CTT"):         cttlist.append (Ctt.get_text ())     ctlist  = []    for ct in  soup.find_all (' span ', class_= "CT"):          ctlist.append (Ct.get_text ())     if  page == 0:        print  "Weibo user profile:"  + cttlist[0 ]        print  "Weibo user personality signature:"  + cttlist[1]         print  "User's Weibo news: \ n"     imgurllist = []     for img in  soup.find_all (' a '):         if img.find (' img ')  is not None :             if  ' Http://tva3. '  not in  img.find (' img ') [' src '] and  ' https://h5 '  not in img.find ( ' img ') [' src ']:                 Imgurllist.append (Img.find (' img ') [' src '])      #imgname  = soup.title.string +   ' _ '  + str (page)  + str (Time.time ())  +str (Random.randrange (0, 1000, 3))   + '. jpg '     if not os.path.exists (str (soup.title.string)):         os.mkdir (str (soup.title.string))      # imgname = './' + str (soup.title.string)  +  '/' + soup.title.string +  ' _ '  +  str (Time.time ())  + '. jpg '     for imgurl in imgurllist:         imgname =  './' + str (soup.title.string)  +  ' /' +soup.title.string +  ' _ '  + str (page)  + str (Time.time ())  +str ( Random.randrange (0, 1000, 3))   + '. jpg '          Response = requests.get ('%s '  % imgurl)         DIRW  = str (soup.title.string)         open (imgname,  ' WB '). Write (response.content)         time.sleep (1.5)      Try:        for i in range (Len (ctlist)):             print cttlist[2+i]             print ctlist[i]             print  "\ n"     except:         for i  In range (Len (ctlist)):             print  cttlist[i]            print ctlist[i]             print  "\ n"      if  "Next page"  not  in  soup.select (' div[id= "pagelist"] ") [0].get_text ():         break    time.sleep (Random.randint (1,3))

Effect Show:

650) this.width=650; "Src=" https://s2.51cto.com/wyfs02/M01/9D/F3/wKioL1mJQLTy1ZkmAAIULD7liww937.png-wh_500x0-wm_ 3-wmp_4-s_2394453633.png "title=" 96.png "alt=" Wkiol1mjqlty1zkmaaiuld7liww937.png-wh_50 "/>

650) this.width=650; "Src=" https://s1.51cto.com/wyfs02/M02/9D/F3/wKioL1mJQvOA6i52AA2OaKf9Pr0595.png-wh_500x0-wm_ 3-wmp_4-s_2720288567.png "title=" 07.png "alt=" Wkiol1mjqvoa6i52aa2oakf9pr0595.png-wh_50 "/>

This article is from the "Shangwei Super" blog, please make sure to keep this source http://9399369.blog.51cto.com/9389369/1954433

Python Crawl Weibo information