python多线程爬取-今日头条的街拍数据（附源码加思路注释）

  这里用的是json+re+requests+beautifulsoup+多线程


1 import json
  2 import re
  3 from multiprocessing.pool import Pool
  4 
  5 import requests
  6 from bs4 import BeautifulSoup
  7 from config import *
  8 from requests import RequestException
  9 
 10 
 11 def get_page_index(offset, keyword):
 12     ‘‘‘得到一个页面的索引‘‘‘
 13     data = {
 14         ‘offset‘: offset,
 15         ‘format‘: ‘json‘,
 16         ‘keyword‘: keyword,
 17         ‘autoload‘: ‘true‘,
 18         ‘count‘: ‘20‘,
 19         ‘cur_tab‘: ‘1‘,
 20         ‘from‘: ‘search_tab‘
 21     }
 22     # 请求方式一
 23     # url = ‘https://www.toutiao.com/search_content/?‘+urlencode(data)
 24     # response = requests.get(url)
 25 
 26     # 请求方式二
 27     url = ‘https://www.toutiao.com/search_content/‘
 28     try:
 29         response = requests.get(url, params=data)
 30         if response.status_code == 200:
 31             return response.text
 32         return None
 33     except RequestException:
 34         return None
 35 
 36 
 37 def parse_page_index(html):
 38     ‘‘‘解析json数据‘‘‘
 39     data = json.loads(html)
 40     if data and ‘data‘ in data.keys():
 41         for item in data.get(‘data‘):
 42             yield item.get(‘article_url‘)
 43 
 44 
 45 def get_page_detail(url):
 46     ‘‘‘得到详情页的数据‘‘‘
 47     # 添加的请求头
 48     headers = {
 49         ‘user-agent‘: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36‘,
 50     }
 51     try:
 52         response = requests.get(url, headers=headers)
 53         if response.status_code == 200:
 54             return response.text
 55         return None
 56     except RequestException:
 57         return None
 58 
 59 
 60 def parse_page_detail(html, url):
 61     ‘‘‘解析详情页数据‘‘‘
 62     soup = BeautifulSoup(html, ‘lxml‘)
 63     t = soup.select(‘title‘)
 64     for i in t:
 65         title = i.get_text()
 66 
 67     pattern = re.compile(‘gallery: JSON.parse\("(.*?)"\),‘, re.S)
 68     result = re.search(pattern, html)
 69     if result:
 70 
 71         # print(result.group(1))
 72         d = re.sub(‘\\\\‘, ‘‘, result.group(1))
 73         # print(d)
 74         data = json.loads(d)
 75         if data:
 76             images = [item.get(‘url‘) for item in data.get(‘sub_images‘)]
 77             for image in images:
 78                 download_image(image, title)
 79             return {
 80                 ‘title‘: title,
 81                 ‘url‘: url,
 82                 ‘images‘: images
 83             }
 84     else:
 85         None
 86 
 87 
 88 def download_image(url, title):
 89     ‘‘‘
 90     图片下载
 91     :param url: 下载的连接
 92     :return:
 93     ‘‘‘
 94     print(‘正在下载‘, url)
 95     try:
 96         response = requests.get(url)
 97         if response.status_code == 200:
 98             content = response.content
 99             save_to_image(content, title)
100         return None
101     except RequestException:
102         return None
103 
104 
105 count = 0
106 
107 
108 def save_to_image(content, title):
109     global count
110     ‘‘‘
111     保存图片文件
112     :param content: 图片文件的内容
113     :return:
114     ‘‘‘
115     name = title + str(count)
116     file_path = ‘./头条/{}.{}‘.format(name, ‘jpg‘)
117     with open(file_path, ‘wb‘) as f:
118         count += 1
119         f.write(content)
120 
121 
122 def main(offset):
123     ‘‘‘主程序入口‘‘‘
124     html = get_page_index(offset, ‘街拍‘)
125 
126     # print(html)
127     for url in parse_page_index(html):
128 
129         if url:
130             # print(url)
131             html = get_page_detail(url)
132             if html:
133                 # print(parse_page_detail(html, url))
134                 result = parse_page_detail(html, url)
135                 if result:
136                     print(result)
137                     # save_to_mongo(result)
138 
139 
140 GROUP_START = 1
141 GROUP_END = 20
142 if __name__ == ‘__main__‘:
143     groups = [i * 20 for i in range(GROUP_START, GROUP_END)]
144     pool = Pool()
145     pool.map(main, groups)