python3简单实现微信爬虫

Python爬虫视频教程零基础小白到scrapy爬虫高手-轻松入门

https://item.taobao.com/item.htm?spm=a1z38n.10677092.0.0.482434a6EmUbbW&id=564564604865

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

# -*- coding: utf-8 -*-

import sys

reload(sys)

import datetime

import time

sys.setdefaultencoding("utf-8")

from ghost import Ghost

ghost = Ghost(wait_timeout=20)

url="http://weixin.sogou.com/gzh?openid=oIWsFt8JDv7xubXz5E3U41T0eFbk"

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

http://www.jb51.net/article/78925.htm

本文给大家分享的是使用python通过搜狗入口，爬取微信文章的小程序，非常的简单实用，有需要的小伙伴可以参考下

本人想搞个采集微信文章的网站，无奈实在从微信本生无法找到入口链接，网上翻看了大量的资料，发现大家的做法总体来说大同小异，都是以搜狗为入口。下文是笔者整理的一份python爬取微信文章的代码，有兴趣的欢迎阅读

#coding:utf-8

author = 'haoning'

**#!/usr/bin/env python

import time

import datetime

import requests**

import json

import sys

reload(sys)

sys.setdefaultencoding( "utf-8" )

import re

import xml.etree.ElementTree as ET

import os

#OPENID = 'oIWsFtyel13ZMva1qltQ3pfejlwU'

OPENID = 'oIWsFtw_-W2DaHwRz1oGWzL-wF9M&ext'

XML_LIST = []

# get current time in milliseconds

current_milli_time = lambda: int(round(time.time() * 1000))

def get_json(pageIndex):

global OPENID

the_headers = {

'User-Agent':

'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'

,

'Referer': 'http://weixin.sogou.com/gzh?openid={0}'.format(OPENID),

'Host': 'weixin.sogou.com'

}

url = 'http://weixin.sogou.com/gzhjs?cb=sogou.weixin.gzhcb&openid={0}&page={1}&t={2}'.format(OPENID, pageIndex, current_milli_time()) #url

print(url)

response = requests.get(url, headers = the_headers)

# TO-DO; check if match the reg

response_text = response.text

print response_text

json_start = response_text.index('sogou.weixin.gzhcb(') + 19

json_end = response_text.index(')') - 2

json_str = response_text[json_start : json_end] #get json

#print(json_str)

# convert json_str to json object

json_obj = json.loads(json_str) #get json obj

# print json_obj['totalPages']

return json_obj

def add_xml(jsonObj):

global XML_LIST

xmls = jsonObj['items'] #get item

#print type(xmls)

XML_LIST.extend(xmls) #用新列表扩展原来的列表

**[#www.oksousou.com][2]**

# ------------ Main ----------------

print 'play it :) '

# get total pages

default_json_obj = get_json(1)

total_pages = 0

total_items = 0

if(default_json_obj):

# add the default xmls

add_xml(default_json_obj)

# get the rest items

total_pages = default_json_obj['totalPages']

total_items = default_json_obj['totalItems']

print total_pages

# iterate all pages

if(total_pages >= 2):

for pageIndex in range(2, total_pages + 1):

add_xml(get_json(pageIndex)) #extend

print 'load page ' + str(pageIndex)

print len(XML_LIST)