爬虫实例爬取微信公众号文章

网站：http://weixin.sogou.com/weixin?type=2&query=python&page=1

实例中含有IP代理池！

import requests, re, pymongo, time

from fake_useragent import UserAgent

from urllib.parse import urlencode
from pyquery import PyQuery
from requests.exceptions import ConnectionError


client = pymongo.MongoClient('localhost')
db = client['weixin']

key_word = 'python开发'
connection_count = 0 # 连接列表页失败的次数
connection_detail_count = 0 # 连接列表页失败的次数

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:60.0) Gecko/20100101 Firefox/60.0',
    'Cookie': 'CXID=161A70BF2483DEF017E035BBBACD2A81; [email protected]@@@@@@@@@@; SUID=57A70FAB5D68860A5B1E1053000BC731; IPLOC=CN4101; SUV=1528705320668261; pgv_pvi=5303946240; ABTEST=5|1528705329|v1; SNUID=EF1FB713B7B2D9EE6E2A6351B8B3F072; weixinIndexVisited=1; sct=2; SUIR=F607AE0BA0A5CFF9D287956DA129A225; pgv_si=s260076544; JSESSIONID=aaaILWONRn9wK_OiUhlnw; PHPSESSID=1i38a2ium8e5th2ukhnufua6r1; ppinf=5|1528783576|1529993176|dHJ1c3Q6MToxfGNsaWVudGlkOjQ6MjAxN3x1bmlxbmFtZToxODolRTklQUQlOTQlRTklOTUlOUN8Y3J0OjEwOjE1Mjg3ODM1NzZ8cmVmbmljazoxODolRTklQUQlOTQlRTklOTUlOUN8dXNlcmlkOjQ0Om85dDJsdUtPQzE0d05mQkJFeUI2d1VJVkhZUE1Ad2VpeGluLnNvaHUuY29tfA; pprdig=ENOZrtvLfoIOct75SgASWxBJb8HJQztLgFbyhRHBfeqrzcirg5WQkKZU2GDCFZ5wLI93Wej3P0hCr_rST0AlvGpF6MY9h24P267oHdqJvgP2DmCHDr2-nYvkLqKs8bjA7PLM1IEHNaH4zK-q2Shcz2A8V5IDw0qEcEuasGxIZQk; sgid=23-35378887-AVsfYtgBzV8cQricMOyk9icd0; ppmdig=15287871390000007b5820bd451c2057a94d31d05d2afff0',
}

def get_proxy():
    try:
        response = requests.get("http://127.0.0.1:5010/get/")
        if response.status_code == 200:
            return response.text
        return None
    except Exception as e:
        print('获取代理异常：',e)
        return None


def get_page_list(url):
    global connection_count
    proxies = get_proxy()
    print('列表页代理：', proxies)

    # 请求url，获取源码
    if proxies != None:
        proxies = {
            'http':'http://'+proxies
        }

    try:
        response = requests.get(url, allow_redirects=False, headers=headers, proxies=proxies)
        if response.status_code == 200:
            print('列表页{}请求成功',url)
            return response.text
        print('状态码：',response.status_code)
        if response.status_code == 302:
            # 切换代理，递归调用当前函数。
            get_page_list(url)
    except ConnectionError as e:
        print('连接对方主机{}失败: {}',url,e)
        connection_count += 1
        if connection_count == 3:
            return None
        # 增加连接次数的判断
        get_page_list(url)


def parse_page_list(html):
    obj = PyQuery(html)
    all_a = obj('.txt-box > h3 > a').items()
    for a in all_a:
        href = a.attr('href')
        yield href


def get_page_detail(url):
    global connection_detail_count
    """
    请求详情页
    :param url: 详情页的url
    :return: 
    """
    proxies = get_proxy()
    print('详情页代理：',proxies)
    # 请求url，获取源码
    if proxies != None:
        proxies = {
            'http': 'http://' + proxies
        }

    try:
        # 注意：将重定向allow_redirects=False删除。列表页是https： verify=False,
        # 注意：将重定向allow_redirects=False删除。列表页是https： verify=False,
        # 注意：将重定向allow_redirects=False删除。列表页是https： verify=False,
        # 注意：将重定向allow_redirects=False删除。列表页是https： verify=False,
        response = requests.get(url, headers=headers, verify=False, proxies=proxies)
        if response.status_code == 200:
            print('详情页{}请求成功', url)
            return response.text
        else:
            print('状态码：', response.status_code,url)
            # 切换代理，递归调用当前函数。
            get_page_detail(url)
    except ConnectionError as e:
        print('连接对方主机{}失败: {}', url, e)
        connection_detail_count += 1
        if connection_detail_count == 3:
            return None
        # 增加连接次数的判断
        get_page_detail(url)

def parse_page_detail(html):
    obj = PyQuery(html)
    # title = obj('#activity-name').text()
    info = obj('.profile_inner').text()
    weixin = obj('.xmteditor').text()

    print('info')

    return {
        'info':info,
        'weixin':weixin
    }


def save_to_mongodb(data):
    # insert_one: 覆盖式的
    db['article'].insert_one(data)

    # 更新的方法：
    # 参数1：指定根据什么字段去数据库中进行查询，字段的值。
    # 参数2：如果经过参数1的查询，查询到这条数据，执行更新的操作；反之，执行插入的操作；$set是一个固定的写法。
    # 参数3：是否允许更新
    db['article'].update_one({'info': data['info']}, {'$set': data}, True)
    time.sleep(1)


def main():
    for x in range(1, 101):
        url = 'http://weixin.sogou.com/weixin?query={}&type=2&page={}'.format(key_word, 1)
        html = get_page_list(url)
        if html != None:
            # 详情页的url
            urls = parse_page_list(html)
            for url in urls:
                detail_html = get_page_detail(url)
                if detail_html != None:
                    data = parse_page_detail(detail_html)
                    if data != None:
                        save_to_mongodb(data)


if __name__ == '__main__':
    main()