数据处理  

json数据处理  
import jsonj = "[{\"name\":\"张三\",\"sex\":\"男\"},{\"name\":\"张三\",\"sex\":\"男\"},{\"name\":\"张三\",\"sex\":\"男\"},{\"name\":\"张三\",\"sex\":\"男\"}]"obj = json.loads(j)#将json 转为 字典s = json.dumps(obj,ensure_ascii=False)#将字典转为jsonprint(s)
eg.
import requestsimport jsonurl = "https://www.toutiao.com";url_json = "https://www.toutiao.com/api/pc/focus/"r = requests.get(url_json)r.encoding="utf-8"text = r.text.encode("utf-8").decode("unicode-escape");obj = json.loads(text)list = []for item in obj["data"]["pc_feed_focus"]: dic = {} dic["name"] = item["title"] dic["url"] = url+item["display_url"] list.append(dic)print(list)with open("d://text.txt",mode="w+",encoding="utf-8") as f: for item in list: text = "%s\n%s\n\n"%(item["name"],item["url"]) f.writelines(text) f.close()print("保存  胜利 ")​
正则表达式

常用的正则表达式办法 re.compile(编译)pattern.match(从头找一个)pattern.search(找一个)pattern.findall(找所有)pattern.sub(替换)

#获取所有的<a>标签中的href和内容response = requests.get(url,headers = header,verify=False)response.encoding = "gbk"text = response.textlist = re.findall("<a.*?href=\"(.*?)\".*?>(.*?)</a>",text)
爬取新闻试试
import requestsimport jsonurl = "https://www.toutiao.com";url_json = "https://www.toutiao.com/api/pc/feed/"​def get_new(url,page): print("第%d页数据\n"%page) par = {"min_behot_time":"0", "category":"__all__", "utm_source":"toutiao", "widen":page, "tadrequire":"true", "as":"A1250B9CAD1D50B", "cp":"5BCD3D15503B1E1", "_signature":"RKT9sBAZH2s.nZ52VHIiUkSk.a" }​ header = { "accept":"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8", "accept-encoding":"gzip, deflate, sdch, br", "accept-language":"zh-CN,zh;q=0.8", "cookie":"uuid=\"w:dcbd0242a9fe484383c6636fe20d060f\"; _ga=GA1.2.1506896000.1534144404; __tea_sdk__ssid=8e3979d0-0146-4a09-981e-4bf22ddcd8da; __tea_sdk__user_unique_id=6614851142792824324; ccid=0889c1662d7c32cf7cfbbaed374fff41; UM_distinctid=16699804cee25c-033cb3b5725eef-2b6f686a-1fa400-16699804cef351; login_flag=5a14c20d209ab052a7978c7086705592; sid_tt=03441da17a2258d893fe14bdc8f89104; sessionid=03441da17a2258d893fe14bdc8f89104; part=stable; sid_guard=\"03441da17a2258d893fe14bdc8f89104|1540173659|2592000|Wed\054 21-Nov-2018 02:00:59 GMT\"; uid_tt=91c220e0eedcd3bbf0f18bf313ce1991; odin_tt=46e7201ef0566449f12c3109272fb067fa703d42c8dc1206cbf5c0230dd35a0ab1f3cf871381c186e229dfd246e5bdc2; tt_webid=6614851142792824324; WEATHER_CITY=%E5%8C%97%E4%BA%AC; CNZZDATA1259612802=1078251197-1540189911-%7C1540211511; __tasessionId=2b1oj444a1540216055134; csrftoken=e26f54e05d0eaaf3697b65190c17d652; tt_webid=6614851142792824324", "upgrade-insecure-requests":"1", "user-agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.98 Safari/537.36 LBBROWSER"} r = requests.get(url_json,params = par,headers = header) r.encoding="utf-8" text = r.text.encode("utf-8").decode("unicode-escape"); print(text) obj = json.loads(text) list = [] if len(obj["data"]) >0: for item in obj["data"]: dic = {} dic["name"] = item["title"] dic["url"] = url+item["source_url"] list.append(dic)  with open("d://text.txt",mode="a+",encoding="utf-8") as f: for item in list: text = "%s\n%s\n\n"%(item["name"],item["url"]) f.writelines(text) f.close() get_new(url_json,page+1) return else: print("保存  胜利 ") return​get_new(url_json,1)print("胜利 ")
文章来源：今日头条(昭通热线网www.ztrxw.cn版权与免责声明：1.本网转载其他媒体，目的在于传递信息，并不代表赞同其观点和对其真实性负责，本网不承担此类稿件侵权行为的连带责任。2.如本网所转载稿件涉及版权等问题，请著作权或版权拥有机构致电或来函与本网联系，本网将在第一时间处理妥当。如有侵犯您的名誉权或其他权利，亦请及时通知本网。电话：0870-2156588 邮箱：信箱：569098112@qq.com。本网在审慎确认后，将即刻予以删除。3.本网原创文章未经允许,私自转载者本网保留追究其版权责任的权利。转载请注明来源昭通热线网www.ztrxw.cn）