該案例調(diào)用搜狗微信公眾號(hào)搜索的接口，實(shí)現(xiàn)了輸入關(guān)鍵字搜索然后返回對(duì)應(yīng)的公眾號(hào)名稱，公眾號(hào)，以及公眾號(hào)描述的功能

# coding:utf-8
import requests
import urllib
from bs4 import BeautifulSoup

# 爬取的網(wǎng)址url：http://weixin.sogou.com/weixin?type=1&s_from=input&query=%E4%BA%A7%E5%93%81&ie=utf8&_sug_=n&_sug_type_=

# 定義獲取url管理器的方法
def get_url(keyword, page):
    urlList = []
    for page in range(page):
        page = page + 1
        firstUrl = 'http://weixin.sogou.com/weixin?type=1&s_from=input&ie=utf8&_sug_=n&_sug_type_=&query='
        lastUrl = '&page='
        kw = urllib.quote(keyword)
        url = firstUrl + kw + lastUrl + str(page)
        urlList.append(url)
    return urlList


# 定義獲取搜索結(jié)果的方法
def get_info(keyword, page):
    urlList = get_url(keyword, page)
    resList = []
    for url in urlList:
        response = requests.get(url)
        res = response.content
        soup = BeautifulSoup(res, 'html.parser')
        nameList = soup.findAll('p', attrs={'class': 'tit'})
        enameList = soup.findAll('label', attrs={'name': 'em_weixinhao'})
        summaryList = soup.select('.gzh-box2 + dl > dd')
        # 分頁(yè)搜索結(jié)果返回的條數(shù)不一致（搜狗的反爬機(jī)制），所以這邊選擇了7作為臨界值，某一個(gè)url返回的大于等于7，則爬取第2頁(yè)，否則不進(jìn)行第2頁(yè)爬取
        # 這里應(yīng)該還有更好的方案，大家可以想一想
        if len(nameList) >= 7:  
            for v in range(len(nameList)):
                resDict = {}
                resDict = {
                    'name': nameList[v].text.strip('\n'),
                    'ename': enameList[v].text,
                    'summary': summaryList[v].text
                }
                resList.append(resDict)
        else:
            for v in range(len(nameList)):
                resDict = {}
                resDict = {
                    'name': nameList[v].text.strip('\n'),
                    'ename': enameList[v].text,
                    'summary': summaryList[v].text
                }
                resList.append(resDict)
            break

    for weixin in resList:
        print '名字：%s' % (weixin['name'].encode('utf-8'))
        print '公眾號(hào)：%s' % (weixin['ename'].encode('utf-8'))
        print '描述：%s' % (weixin['summary'].encode('utf-8'))
        print '\n'


if __name__ == '__main__':
    keyword = raw_input('請(qǐng)輸入關(guān)鍵字：')
    page = input('請(qǐng)輸入搜索結(jié)果的頁(yè)數(shù)：')
    get_info(keyword, page)