python_爬虫今日头条

from urllib.parse import urlencode
from requests.exceptions import RequestException
import requests
import json
import re
from bs4 import BeautifulSoup
from config  import *
import pymongo
client = pymongo.MongoClient(MONGO_URL)
db = client(MONGO_DB)
 
def save_to_mogo(result):
    if db[MONGO_TABLE].insert(result):
        print("储存成功",result)
        return True
    return False
def get_page_index(offset,keyword):
    print(1)
    data={
        'offset': offset,
        'format': 'json',
        'keyword': keyword,
        'autoload': 'true',
        'count': '20',
        'cur_tab': 1,
    }
    url ='https://www.toutiao.com/search_content/?'+urlencode(data)
 
    r=requests.get(url)
    try:
        if r.status_code ==200:
            r.encoding = r.apparent_encoding
            return r.text
        return None
    except RequestException:
        print("请求页面错误")
        return None
def parse_page_index(html):
    data =json.loads(html)
    if data and "data" in data.keys():
        for item in data.get("data"):
            yield item.get("article_url")
 
def get_pic_url(url):
    try:
        r=requests.get(url)
        if r.status_code==200:
            return r.text
        return None
    except RequestException:
        return None
def get_pic(html,url):
    soup=BeautifulSoup(html,'html.parser')
    title=soup.select('title')[0].get_text()
 
    images_pattern = re.compile('gallery = (.*?);',re.S)
    result = re.search(images_pattern,html)
    if result:
        data = json.loads(result.group(1))
        if data and 'sub_images' in data.keys():
            sub_images = data.get('sub_images')
            images=[item.get('url') for item in sub_images]
            return {
                'title':title,
                'images':images,
                'url':url
            }
 
def main():
    html= get_page_index(0, "街拍")
    parse_page = parse_page_index(html)
    for url in  parse_page:
            html =get_pic_url(url)
            if html:
                if get_pic(html,url) is not None:
                    result = get_pic(html,url)
                    save_to_mogo(result)
 
if __name__ == '__main__':
    main()