#!/usr/bin/env python
# -*- coding:utf-8 -*-
"""
@author:Aiker
@file:toutiao.py
@time:下午9:35
"""
import json
import os
import re
from json import JSONDecodeError
from multiprocessing import Pool
from urllib.parse import urlencode
from hashlib import md5
import pymongo
import requests
from requests.exceptions import RequestException
MONGO_URL = ‘localhost:27017‘
MONGO_DB = ‘toutiao‘
MONGO_TABLE = ‘toutiao‘
GROUP_START = 1
GROUP_END = 20
KEYWORD = ‘街拍‘
client = pymongo.MongoClient(MONGO_URL, connect=False)
db = client[MONGO_DB]
headers = {
‘user-agent‘: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36‘
}
def get_url(url):
try:
response = requests.get(url, headers=headers)
if response.status_code == 200:
return response.text
return None
except RequestException:
print(‘请求失败‘, url)
return None
def get_page_index(offset, keyword):
data = {
‘aid‘: ‘24‘,
‘app_name‘: ‘web_search‘,
‘offset‘: offset,
‘format‘: ‘json‘,
‘keyword‘: keyword,
‘autoload‘: ‘true‘,
‘count‘: ‘20‘,
‘en_qc‘: ‘1‘,
‘cur_tab‘: ‘1‘,
‘from‘: ‘search_tab‘,
‘pd‘: ‘synthesis‘,
‘timestamp‘: ‘1124216535987‘
}
url = ‘https://www.toutiao.com/api/search/content/?‘ + urlencode(data) # 字典对象转化url对象
try:
response = requests.get(url, headers=headers)
if response.status_code == 200:
return response.text
return None
except RequestException:
print(‘请求索引页失败‘)
return None
def parse_page_index(html):
try:
data = json.loads(html) # 转化为json对象
if data and ‘data‘ in data.keys():
# print(data.keys()) #调试,输出所有key
for item in data.get(‘data‘):
if ‘article_url‘ in item: # 判断是否存在,避免出现None
# print(item)
yield item.get(‘article_url‘) # 构造生成器
except JSONDecodeError:
pass
except TypeError:
pass
def get_page_detail(url):
try:
response = requests.get(url, headers=headers)
if response.status_code == 200:
return response.text
return None
except RequestException:
print(‘请求详情页出错‘, url)
return None
def parse_page_detail(html, url):
pattern = re.compile("articleInfo:.*?title:\s‘(.*?)‘,.*?content:\s‘(.*?)‘.*?groupId", re.S)
result = re.findall(pattern, html)
# print(tc)
if result:
title, content = result[0]
pattern = re.compile("(http://.*?)"", re.S)
images = re.findall(pattern, content)
# print(img)
for image in images: download_image(image, title)
# print(item)
return {
‘title‘: title,
‘url‘: url,
‘images‘: images
}
else:
pattern = re.compile(‘BASE_DATA.galleryInfo.*?title:\s\‘(.*?)\‘.*?gallery: JSON.parse\("(.*)"\)‘, re.S)
result = re.findall(pattern, html)
# print(result[0])
if result:
title, content = result[0]
data = json.loads(content.replace(‘\\‘, ‘‘))
# print(data)
if data and ‘sub_images‘ in data.keys():
sub_images = data.get(‘sub_images‘)
images = [item.get(‘url‘) for item in sub_images]
for image in images: download_image(image,title)
return {
‘title‘: title,
‘url‘: url,
‘images‘: images
}
def save_to_mongo(result):
if db[MONGO_TABLE].insert(result):
print(‘存储到MongoDB成功‘, result)
return True
return False
def download_image(url,title):
print(‘正在下载‘, url)
try:
response = requests.get(url)
if response.status_code == 200:
save_image(response.content,title)
return None
except RequestException:
print(‘请求图片出错‘, url)
return None
def save_image(content,title):
try:
if title:
title = re.sub(‘[:?!!:?]‘, ‘‘, title) # 替换title中的特殊字符,避免建立资料夹目录出错
dir = ‘z:\\toutiao\\‘
if os.path.exists(dir + title):
pass
else:
os.mkdir(dir + title)
file_path = ‘{0}/{1}.{2}‘.format( dir + title, md5(content).hexdigest(), ‘jpg‘)
if not os.path.exists(file_path):
with open(file_path, ‘wb‘) as f:
f.write(content)
f.close()
except OSError:
pass
def main(offset):
html = get_page_index(offset, KEYWORD)
for url in parse_page_index(html):
print(url)
html = get_page_detail(url)
if html:
result = parse_page_detail(html, url)
if result:
save_to_mongo(result)
# print(html)
if __name__ == ‘__main__‘:
# main()
groups = [x * 20 for x in range(GROUP_START, GROUP_END + 1)]
pool = Pool()
pool.map(main, groups)
pool.close()
pool.join()
- 下载图片,并保存到mongodb
原文地址:https://blog.51cto.com/m51cto/2374411
时间: 2024-10-03 19:17:29