使用ghost.py 通过搜搜 的微信搜索来爬取微信公共账号的信息
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
|
# -*- coding: utf-8 -*-
import sys
reload(sys)
import datetime
import time
sys.setdefaultencoding("utf-8")
from ghost import Ghost
ghost = Ghost(wait_timeout=20)
page,resources = ghost.open(url)
result, resources = ghost.wait_for_selector("#wxmore a")
from bs4 import BeautifulSoup
c=0
while True:
if c>=30:
break
soup = BeautifulSoup(ghost.content)
for wx in soup.find_all("h4"):
print wx
page, resources = ghost.evaluate(
"""
var div1 = document.getElementById("wxbox");
div1.innerHTML = '';
""")
ghost.click("#wxmore a")
result, resources = ghost.wait_for_selector(".wx-rb3")
c=c+1
pass
|
以上所述就是本文的全部内容了，希望对大家学习Python能够有所帮助