本文实例为大家分享了python采集微信公众号文章的具体代码,供大家参考,具体内容如下
在python一个子目录里存2个文件,分别是:采集公众号文章.py和config.py。 代码如下:
1.采集公众号文章.py
from urllib.parse import urlencode
import pymongo
import requests
from lxml.etree import xmlsyntaxerror
from requests.exceptions import connectionerror
from pyquery import pyquery as pq
from config import *
#配置mongodb
client = pymongo.mongoclient(mongo_uri)
db = client[mongo_db]
base_url = 'http://weixin.sogou.com/weixin?'
#添加头文件
headers = {
'cookie': 'usid=s-pkm6vw_ac4ktr1; suv=00a75e9078efd9f75a6573ecad0ec883; wuid=aagcxershqaaaaqrgn4soagaaaa=; iploc=cn4414; suid=767beab73220910a000000005aa9e2aa; pgv_pvi=159197184; pgv_si=s8252565504; abtest=0|1521083055|v1; weixinindexvisited=1; sct=1; jsessionid=aaalxqkrp6jjs8ac4hwhw; ppinf=5|1521083238|1522292838|dhj1c3q6mtoxfgnsawvudglkojq6mjaxn3x1bmlxbmftzto2oiuzqsuyoxxjcnq6mta6mtuymta4mzizohxyzwzuawnrojy6jtnbjti5fhvzzxjpzdo0ndpvoxqybhvoaexncs1vlw1zbjmxmmnmskp4ogpzqhdlaxhpbi5zb2h1lmnvbxw; pprdig=tbvf7qlzddmjpcn4jtf3dg8c8nerx-ygdi8kucezn0rtewuhkgu4xmnaxzbakvquswboigl_rd-34abu6vy9jkv7me3bypigydniv2ljuchgco7gk58m9qhrm3aa7nhlhjfvyoaqkqgbsykpatxmnpe3tm57zdlzdpg_8mbmbnq; sgid=23-30671195-avqp42zctqiacybbdvvfwno4; phpsessid=4jjk2a9rv6kq7m50f42r92u3r3; suir=d2df4e12a5a1c3ce1a8ad7f2a5fe18fe; ppmdig=1521087492000000855f9824f94abe82b25d2839135ad3a8; snuid=fef36d3f8882efec4fcf61e68801da49; seccoderight=success; successcount=1|thu, 15 mar 2018 04:23:23 gmt',
'host': 'weixin.sogou.com',
'referer': 'http://weixin.sogou.com/antispider/?from=%2fweixin%3fquery%3d%e9%a3%8e%e6%99%af%26type%3d2%26page%3d95%26ie%3dutf8',
'upgrade-insecure-requests': '1',
'user-agent': 'mozilla/5.0 (macintosh; intel mac os x 10_11_6) applewebkit/537.36 (khtml, like gecko) chrome/65.0.3325.146 safari/537.36'
}
#初始化代理为本地ip
proxy = none
#定义获取代理函数
def get_proxy():
try:
response = requests.get(proxy_pool_url)
if response.status_code == 200:
return response.text
return none
except connectionerror:
return none
#添加代理获取网页内容
def get_html(url, count=1):
print('crawling', url)
print('trying count', count)
global proxy
if count >= max_count:
print('tried too many counts')
return none
try:
if proxy:
proxies = {
'http': 'http://' + proxy
}
response = requests.get(url, allow_redirects=false, headers=headers, proxies=proxies)
else:
response = requests.get(url, allow_redirects=false, headers=headers)
if response.status_code == 200:
return response.text
if response.status_code == 302:
# need proxy
print('302')
proxy = get_proxy()
if proxy:
print('using proxy', proxy)
return get_html(url)
else:
print('get proxy failed')
return none
except connectionerror as e:
print('error occurred', e.args)
proxy = get_proxy()
count += 1
return get_html(url, count)
#获取索引页内容
def get_index(keyword, page):
data = {
'query': keyword,
'type': 2,
'page': page
}
queries = urlencode(data)
url = base_url + queries
html = get_html(url)
return html
#解析索引页,提取详情页网址
def parse_index(html):
doc = pq(html)
items = doc('.news-box .news-list li .txt-box h3 a').items()
for item in items:
yield item.attr('href')
#获取详情页
def get_detail(url):
try:
response = requests.get(url)
if response.status_code == 200:
return response.text
return none
except connectionerror:
return none
#解析索引页,返回微信文章标题、内容、日期、公众号名称等
def parse_detail(html):
try:
doc = pq(html)
title = doc('.rich_media_title').text()
content = doc('.rich_media_content').text()
date = doc('#post-date').text()
nickname = doc('#js_profile_qrcode > div > strong').text()
wechat = doc('#js_profile_qrcode > div > p:nth-child(3) > span').text()
return {
'title': title,
'content': content,
'date': date,
'nickname': nickname,
'wechat': wechat
}
except xmlsyntaxerror:
return none
#存储到mongodb,去重操作
def save_to_mongo(data):
if db['articles'].update({'title': data['title']}, {'$set': data}, true):
print('saved to mongo', data['title'])
else:
print('saved to mongo failed', data['title'])
#主函数
def main():
for page in range(1, 101):
html = get_index(keyword, page)
if html:
article_urls = parse_index(html)
for article_url in article_urls:
article_html = get_detail(article_url)
if article_html:
article_data = parse_detail(article_html)
print(article_data)
if __name__ == '__main__':
main()
2.config.py代码:
#爬取公众号文章
proxy_pool_url = 'http://127.0.0.1:5000/get'
keyword ='计算机等级二级' # 输入关键词
mongo_uri = 'localhost'
mongo_db = 'data'
max_count = 5
其中,config.py中keyword为查找关键词,可以根据需要更改。经实测,运行"采集公众号文章.py"成功!若因受限不成功,可多运行几次。
以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持萬仟网。
如您对本文有疑问或者有任何想说的,请点击进行留言回复,万千网友为您解惑!