程序代码：

import requests as r
import re
import time as t

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/\
    65.0.3325.181 Safari/537.36'
}
client = pmg.MongoClient('localhost', 27017)
mydb = client['mydb']
d = mydb['doupochangqiong']
a = []

try:
    def get_info(url):
        global a
        res = r.get(url, headers=headers)
        if res.status_code == 200:
            contents = re.findall('<p>(.*?)</p>', res.content.decode('utf-8'), re.S)
            for content in contents:
                content = re.sub(' www. ', '', content)
                content = re.sub('&\\w;','"',content)
                a.append(content)
        else:
            pass

    if __name__ == '__main__':
        urls = ['http://www.{}.html'.format(str(i)) for i in range(1, 1665)]
        for urla in urls:
            get_info(url=urla)
            t.sleep(1)
        b = ''
        b += a[c-1: c]for c in range(1, len(a) + 1)
        info = {'dou': b}
        d.insert_one(info)
except:
    pass

[此贴子已经被作者于2018-7-12 17:51编辑过]