自己练习百度贴吧-中国好声音评论爬爬

Posted 2021-01-07 zhuzhubaoya

 

百度贴吧-中国好声音评论爬爬

 1 # coding=utf-8
 2 import csv
 3 import random
 4 import io
 5 from urllib import request,parse,error
 6 import http.cookiejar
 7 import urllib
 8 import re
 9 from bs4 import BeautifulSoup
10 
11 # 爬爬网址
12 #homeUrl ="http://tieba.baidu.com" #贴吧首页
13 subUrl = "http://tieba.baidu.com/f?kw=%E4%B8%AD%E5%9B%BD%E5%A5%BD%E5%A3%B0%E9%9F%B3&ie=utf-8&pn=0" #中国好声音贴吧页面
14 #childUrl="http://tieba.baidu.com/p/5825125387" #中国好声音贴吧第一条
15 
16 #存储csv文件路径
17 outputFilePath = "E:scriptpython-scriptlaidutiebapapacsvfile_output.csv"
18 
19 def GetWebPageSource(url):
20 
21     values = {}
22     data = parse.urlencode(values).encode(‘utf-8‘)
23 
24     # header
25     user_agent = ""
26     headers = {‘User-Agent‘:user_agent,‘Connection‘:‘keep-alive‘}
27 
28     # 声明cookie 声明opener
29     cookie_filename = ‘cookie.txt‘
30     cookie = http.cookiejar.MozillaCookieJar(cookie_filename)
31     handler = urllib.request.HTTPCookieProcessor(cookie)
32     opener = urllib.request.build_opener(handler)
33 
34     # 声明request
35     request=urllib.request.Request(url, data, headers)
36     # 得到响应
37     response = opener.open(request)
38     html=response.read().decode(‘utf-8‘)
39     # 保存cookie
40     cookie.save(ignore_discard=True,ignore_expires=True)
41 
42     return  html
43 
44     # 将读取的内容写入一个新的csv文档
54 # 主函数
55 if __name__ == "__main__":
56     #outputString = []
57     maxSubPage=2 #中国好声音贴吧翻几页设置？
58     m=0#起始页数
59     with open("E:scriptpython-scriptlaidutiebapapacsvfile_output.csv", "w", newline="", encoding=‘utf-8‘) as datacsv:
60         headers = [‘title‘, ‘url‘, ‘comment‘]
61         csvwriter = csv.writer(datacsv, headers)
62         for n in range(1, int(maxSubPage)):
63             subUrl = "http://tieba.baidu.com/f?kw=%E4%B8%AD%E5%9B%BD%E5%A5%BD%E5%A3%B0%E9%9F%B3&ie=utf-8&pn=" + str(m) + ".html"
64             print(subUrl)
65             subhtml = GetWebPageSource(subUrl)
66             #print(html)
67             # 利用BeatifulSoup获取想要的元素
68             subsoup = BeautifulSoup(subhtml, "lxml")
69             #打印中国好声音贴吧页标题
70             print(subsoup.title)
71             #打印中国好声音第一页贴吧标题
72             all_titles = subsoup.find_all(‘div‘, class_="threadlist_title pull_left j_th_tit ")  # 提取有关与标题
73             for title in all_titles:
74                 print(‘--------------------------------------------------‘)
75                 print("贴吧标题："+title.get_text())#贴吧各标题题目
76                 commentUrl = str(title.a[‘href‘])
77                 #print(commitment)
78                 #评论页循环需要改改，maxchildpage
79                 childPage = 1#评论页翻页变量
80                 maxChildPage = 6#【变量】几页就翻几页设置？
81                 for n in range(1, int(maxChildPage)):
82                     childUrl = "http://tieba.baidu.com" + commentUrl +"?pn=" + str(childPage)
83                     print("贴吧Url："+childUrl)
84                     childhtml = GetWebPageSource(childUrl)
85                     childsoup = BeautifulSoup(childhtml, "lxml")
86                     all_comments = childsoup.find_all(‘div‘, class_="d_post_content_main")  # 提取有关与评论
87                     for comment in all_comments:
88                         print("用户评论：" + comment.get_text())  # 贴吧各标题题目
89                         #outputString.append([title.get_text(), childUrl, comment.get_text()])
90                         csvwriter.writerow([title.get_text(), childUrl, comment.get_text()])
91                     print(‘--------------------------------------------------‘)
92                     childPage = childPage + 1
93                 m = m + 50  # 翻页控制，通过观察发现，每页相差50

跑完了成果图

csv文档中效果

上方生成的csv文件通过txt记事本打开另存为ANIS编码方式，然后在通过csv打开就不会再乱码了，解决csv打开乱码问题相关可以参考博文：https://www.cnblogs.com/zhuzhubaoya/p/9675203.html