python如何爬取搜狗微信公众号文章永久链接的思路解析

这篇文章主要介绍了python如何爬取搜狗微信公众号文章永久链接的思路解析 ,小编觉得挺不错的，现在分享给大家，也给大家做个参考。一起跟随小编过来看看吧。

本文主要讲解思路，代码部分请自行解决

• 搜狗微信搜素获取公众号及文章

• 通过微信公众平台获取永久链接

• python+scrapy框架

• mysql数据库存储+读取公众号

---

获取搜狗微信上当天的信息排名

指定输入关键字，通过scrapy抓取公众号

通过登陆微信公众号链接，获取cookie信息

由于模拟登陆微信公众平台还未解决，因此需要手动登陆，实时获取cookie信息




在这里可以实现转变永久链接

代码部分

def parse(self, response):
            item = SougouItem()
            item["title"] = response.xpath('//title/text()').extract_first()
            print("**"*5, item["title"],"**"*5)
            name = input("----------请输入需要搜索的信息：")
            print(name)
            url = "http://weixin.sogou.com/weixin?query="+name+"&type=2&page=1&ie=utf8"
            yield scrapy.Request(url=url, callback=self.parse_two, meta={"name":name})

搜狗微信中会出现访问频率过快，导致需要输入验证码

 def parse_two(self, response):
     print(response.url)
     name = response.meta["name"]
     resp = response.xpath('//ul[@class="news-list"]/li')
     s = 1
     # 判断url 是否是需要输入验证码
     res = re.search("from", response.url)     # 需要验证码验证
     if res:
         print(response.url)
         img = response.xpath('//img/@src').extract()
         print(img)
         url_img = "http://weixin.sogou.com/antispider/"+ img[1]
         print(url_img)
         url_img = requests.get(url_img).content         with open("urli.jpg", "wb") as f:
             f.write(url_img)             # f.close()
         img = input("请输入验证码:")
         print(img)
         url = response.url
         r = re.search(r"from=(.*)",url).group(1)
         print(r)
         postData = {"c":img,"r":r,"v":"5"}
         url = "http://weixin.sogou.com/antispider/thank.php"
         yield scrapy.FormRequest(url=url, formdata=postData, callback=self.parse_two,meta={"name":name})     
         # 不需要验证码验证
     else:   
        for res, i in zip(resp, range(1, 10)):
             item = SougouItem()
             item["url"] = res.xpath('.//p[1]/a/@href').extract_first()
             item["name"] = name
             print("第%d条" % i)             # 转化永久链接
             headers = {"Host": "mp.weixin.qq.com",                        
             "Connection": "keep-alive",                        
             "Accept": "application/json, text/javascript, */*; q=0.01",                        
             "X-Requested-With": "XMLHttpRequest",                        
             "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36",                        
             "Referer": "https://mp.weixin.qq.com/cgi-bin/appmsg?t=media/appmsg_edit_v2&action=edit&isNew=1&type=10&token=938949250&lang=zh_CN",                        
             "Accept-Encoding": "gzip, deflate, br",                        
             "Accept-Language": "zh-CN,zh;q=0.9",                        
             "Cookie": "noticeLoginFlag=1; pgv_pvi=5269297152; pt2gguin=o1349184918; RK=ph4smy/QWu; ptcz=f3eb6ede5db921d0ada7f1713e6d1ca516d200fec57d602e677245490fcb7f1e; pgv_pvid=1033302674; o_cookie=1349184918; pac_uid=1_1349184918; ua_id=4nooSvHNkTOjpIpgAAAAAFX9OSNcLApfsluzwfClLW8=; mm_lang=zh_CN; noticeLoginFlag=1; remember_acct=Liangkai318; rewardsn=; wxtokenkey=777; pgv_si=s1944231936; uuid=700c40c965347f0925a8e8fdcc1e003e; ticket=023fc8861356b01527983c2c4765ef80903bf3d7; ticket_id=gh_6923d82780e4; cert=L_cE4aRdaZeDnzao3xEbMkcP3Kwuejoi; data_bizuin=3075391054; bizuin=3208078327; data_ticket=XrzOnrV9Odc80hJLtk8vFjTLI1vd7kfKJ9u+DzvaeeHxZkMXbv9kcWk/Pmqx/9g7; slave_sid=SWRKNmFyZ1NkM002Rk9NR0RRVGY5VFdMd1lXSkExWGtPcWJaREkzQ1BESEcyQkNLVlQ3YnB4OFNoNmtRZzdFdGpnVGlHak9LMjJ5eXBNVEgxZDlZb1BZMnlfN1hKdnJsV0NKallsQW91Zjk5Y3prVjlQRDNGYUdGUWNFNEd6eTRYT1FSOEQxT0MwR01Ja0Vo; slave_user=gh_6923d82780e4; xid=7b2245140217dbb3c5c0a552d46b9664; openid2ticket_oTr5Ot_B4nrDSj14zUxlXg8yrzws=D/B6//xK73BoO+mKE2EAjdcgIXNPw/b5PEDTDWM6t+4="}
     respon = requests.get(url=item["url"]).content
     gongzhongh = etree.HTML(respon).xpath('//a[@id="post-user"]/text()')[0]             
     # times = etree.HTML(respon).xpath('//*[@id="post-date"]/text()')[0]
     title_one = etree.HTML(respon).xpath('//*[@id="activity-name"]/text()')[0].split()[0]
     print(gongzhongh, title_one)
     item["tit"] = title_one
     item["gongzhongh"] = gongzhongh             
     # item["times"] = times
     url = "https://mp.weixin.qq.com/cgi-bin/searchbiz?action=search_biz&token=938949250&lang=zh_CN&f=json&ajax=1&query=" + gongzhongh + "&begin=0&count=5"
     # wenzhang_url = "https://mp.weixin.qq.com/cgi-bin/appmsg?token=610084158&lang=zh_CN&f=json&ajax=1&random=0.7159556076774083&action=list_ex&begin=0&count=5&query=" + item["tit"] + "&fakeid=MzA5MzMxMDk3OQ%3D%3D&type=9"
     resp = requests.get(url=url, headers=headers).content
     print(resp)
     faskeids = json.loads(resp.decode("utf-8"))             
     try:
            list_fask = faskeids["list"]             except Exception as f:
     print("**********[INFO]:请求失败，登陆失败， 请重新登陆*************")                
     return
     for fask in list_fask:
                 fakeid = fask["fakeid"]
                 nickname = fask["nickname"]                 if nickname == item["gongzhongh"]:
                     url = "https://mp.weixin.qq.com/cgi-bin/appmsg?token=938949250&f=json&action=list_ex&count=5&query=&fakeid=" + fakeid + "&type=9"
                     # url = "https://mp.weixin.qq.com/cgi-bin/appmsg?token=1773340085&lang=zh_CN&f=json&ajax=1&action=list_ex&begin=0&count=5&query=" + item["tit"] + "&fakeid=MzA5MzMxMDk3OQ%3D%3D&type=9"
                     url = "https://mp.weixin.qq.com/cgi-bin/appmsg?token=938949250&f=json&ajax=1&action=list_ex&begin=0&count=5&query=" + item["tit"] +"&fakeid=" + fakeid +"&type=9"
                     resp = requests.get(url=url, headers=headers).content
                     app = json.loads(resp.decode("utf-8"))["app_msg_list"]
                     item["aid"] = app["aid"]
                     item["appmsgid"] = app["appmsgid"]
                     item["cover"] = app["cover"]
                     item["digest"] = app["digest"]
                     item["url_link"] = app["link"]
                     item["tit"] = app["title"]
                     print(item)
                     time.sleep(10)                 #     time.sleep(5)
                 #     dict_wengzhang = json.loads(resp.decode("utf-8"))
                 #     app_msg_list = dict_wengzhang["app_msg_list"]
                 #     print(len(app_msg_list))
                 #     for app in app_msg_list:
                 #         print(app)
                 #         title = app["title"]
                 #         if title == item["tit"]:
                 #             item["url_link"] = app["link"]
                 #             updata_time = app["update_time"]
                 #             item["times"] = time.strftime("%Y-%m-%d %H:%M:%S", updata_time)
                 #             print("最终链接为:", item["url_link"])
                 #             yield item
                 #         else:
                 #             print(app["title"], item["tit"])
                 #             print("与所选文章不同放弃")
                 #             # item["tit"] = app["title"]
                 #             # item["url_link"] = app["link"]
                 #             # yield item
                 # else:
                 #     print(nickname, item["gongzhongh"])
                 #     print("与所选公众号不一致放弃")
             # time.sleep(100)
             # yield item
             if response.xpath('//a[@class="np"]'):
                 s += 1
                 url = "http://weixin.sogou.com/weixin?query="+name+"&type=2&page="+str(s)                 # time.sleep(3)
                 yield scrapy.Request(url=url, callback=self.parse_two, meta={"name": name})

Atas ialah kandungan terperinci python如何爬取搜狗微信公众号文章永久链接的思路解析 . Untuk maklumat lanjut, sila ikut artikel berkaitan lain di laman web China PHP!