python爬取今日头条图片
from urllib.parse import urlencode
from requests import codes
import os
# qianxiao996精心制作
#博客地址:https://blog.csdn.net/qq_36374896
from hashlib import md5
from multiprocessing.pool import Pool
def get_page(offset):
params = {
'offset': offset,
'format': 'json',
'keyword': '街拍',
'autoload': 'true',
'count': '20',
'cur_tab': '1',
'from': 'search_tab'
}
base_url = 'https://www.toutiao.com/search_content/?'
url = base_url + urlencode(params)
try:
resp = requests.get(url)
if codes.ok == resp.status_code:
return resp.json()
except requests.ConnectionError:
return None
def get_images(json):
if json.get('data'):
data = json.get('data')
for item in data:
if item.get('cell_type') is not None:
continue
title = item.get('title')
images = item.get('image_list')
# url_temp = image.get('url')
for image in images:
url_temp = image.get('url')
yield {
#此处更新,使用列表网址后23位作为大图的地址,抓取大图
'image': 'https:' + '//p3.pstatp.com/large/pgc-image/'+ url_temp[-23:],
# 'image': 'https:' + image.get('url'),
'title': title
}
def save_image(item):
img_path = 'img' + os.path.sep + item.get('title')
if not os.path.exists(img_path):
os.makedirs(img_path)
try:
resp = requests.get(item.get('image'))
if codes.ok == resp.status_code:
file_path = img_path + os.path.sep + '{file_name}.{file_suffix}'.format(
file_name=md5(resp.content).hexdigest(),
file_suffix='jpg')
if not os.path.exists(file_path):
with open(file_path, 'wb') as f:
f.write(resp.content)
print('Downloaded image path is %s' % file_path)
else:
print('Already Downloaded', file_path)
except requests.ConnectionError:
print('Failed to Save Image,item %s' % item)
def main(offset):
json = get_page(offset)
for item in get_images(json):
print(item)
save_image(item)
GROUP_START = 0
GROUP_END = 3
if __name__ == '__main__':
pool = Pool()
groups = ([x * 20 for x in range(GROUP_START, GROUP_END + 1)])
pool.map(main, groups)
pool.close()
pool.join()
代码年代久远,注释当时没写,现在懒得写了
以上是 python爬取今日头条图片 的全部内容, 来源链接: utcz.com/z/388437.html