DONEWS新闻抓取 | 每日爬虫

Posted 2020-10-28 pymkl

# coding=utf-8
import requests
from lxml import etree
#
#
# class DonewsSpider(object):
#     """
#     抓取www.donows.com专栏新闻
#     """
#     def __init__(self):
#         self.start_url = ‘http://www.donews.com/idonews/‘
#         self.headers = {
#             ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/64.0.3282.119 Safari/537.36‘,
#         }
#         self.proxies = {
#             "https": "115.230.51.12:46939",
#         }
#         self.total_list = []
#
#     def get_page(self, url):
#         response = requests.get(url, headers=self.headers, proxies=self.proxies)
#         # response.encoding = response.apparent_encoding
#         return response.text
#
#     def parse(self, page_data):
#         detail_url_list = []
#         html = etree.HTML(page_data)
#         el_objs = html.xpath(‘/html/body/div[5]/div[2]/div/dl‘)
#         for el in el_objs:
#             detail_url = el.xpath(‘./dd/h3/a/@href‘)[0]
#             print(detail_url)
#             if ‘http‘ in detail_url:
#                 detail_url_list.append(detail_url)
#         print(detail_url_list)
#         return detail_url_list
#
#     def parse_detail(self, detail_data):
#         data_dict = {}
#         content_ = ‘‘
#         html = etree.HTML(detail_data)
#         data_dict[‘title_‘] = html.xpath(‘//*[@id="main"]/div[1]/h2/text()‘)[0]
#         content_objs = html.xpath(‘//*[@id="main"]/div[1]/div[2]‘)
#         for p_ in content_objs:
#             content_ += p_.xpath(‘./p/text()‘)[0]
#         data_dict[‘content_‘] = content_
#         data_dict[‘writer_‘] = html.xpath(‘//*[@id="main"]/div[1]/div[1]/p/span[1]/text()‘)[0]
#         return data_dict
#
#     def run(self):
#         page_data = self.get_page(self.start_url)
#         detail_url_list = self.parse(page_data)
#         for url in detail_url_list:
#             detail_data = self.get_page(url)
#             data_dict = self.parse_detail(detail_data)
#             print(data_dict)
#             self.total_list.append(data_dict)
#         print(self.total_list)
#         # 点击获取下拉数据
#         # ... 解析js时,发现数据已经通过ajax存放在一个url中了;
#
# if __name__ == ‘__main__‘:
#     dn_spider = DonewsSpider()
#     dn_spider.run()
#
import re

# 在js中解析出所有detail_url
# 以下是逻辑代码,就不封装了,懒...
headers = {
    ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.119 Safari/537.36‘,
}
proxies = {
    "https": "115.230.51.12:46939",
}
i = 1
detail_url_list = []
data_list = []
while True:
    i += 1
    try:
        url = "http://www.donews.com/column/more_article_ajax?page=%s" % i
        page_data = requests.get(url, headers=headers, proxies=proxies).text.encode(‘utf-8‘)
        # 将unicode数据转化成python数据类型
        url_list = re.findall(r‘http:\\/\\/www.donews.com\\/article\\/detail\\/\d+\\/\d+.html‘, page_data)
        url_ = ‘‘
        for url in url_list:
            url_ = ‘‘
            el_list = url.split(‘\\‘)
            for el in el_list:
                url_ += el
            detail_url_list.append(url_)
            print(detail_url_list)
    except:
        print(‘链接获取完毕,提取页面数据‘)
        for detail_url in detail_url_list:
            detail_page_data = requests.get(detail_url, headers=headers, proxies=proxies).text
            data_dict = {}
            content_ = ‘‘
            html = etree.HTML(detail_page_data)
            data_dict[‘title_‘] = html.xpath(‘//*[@id="main"]/div[1]/h2/text()‘)[0]
            content_objs = html.xpath(‘//*[@id="main"]/div[1]/div[2]‘)
            for p_ in content_objs:
                content_ += p_.xpath(‘./p/text()‘)[0]
            data_dict[‘content_‘] = content_
            data_dict[‘writer_‘] = html.xpath(‘//*[@id="main"]/div[1]/div[1]/p/span[1]/text()‘)[0]
            data_list.append(data_dict)
        print(data_list)