论坛 › Python交流 › python简单爬虫实例-----爬取豆瓣妹子的照片

cuishitian77 发表于 2018-2-6 03:24:53

看看，嘿嘿嘿

hellopyth 发表于 2018-2-6 22:52:10

学习学习

回不去的鱼 发表于 2018-2-6 23:33:07

学习学习

hldn 发表于 2018-2-7 14:44:47

学习

ccksam 发表于 2018-2-7 21:10:26

wow genius!

leyanqz 发表于 2018-2-7 23:39:55

果然不错！

picklove 发表于 2018-2-8 00:23:31

{:5_92:}66666666666

1109353812 发表于 2018-2-8 20:02:42

666

Ojia 发表于 2018-2-10 16:38:22

回复

xujingyu 发表于 2018-2-10 21:42:17

{:5_90:}

lww31538 发表于 2018-2-12 00:33:13

import os
import re
import requests

def get_urls(url, regex):
    urls = []
    base_url = 'http://desk.zol.com.cn'
    content = requests.get(url).content
    area = re.search(regex, content, re.S).group(0)
    tails = re.findall(r'href="(.*?)"', area)
    for tail in tails:
      urls.append(base_url + tail)
    return urls

def download_picture(url, count):
    target_dir = 'pic'
    if os.path.exists(target_dir):
      if not os.path.isdir(target_dir):
            os.remove(target_dir)
    else:
      os.mkdir(target_dir)
    content = requests.get(url).content
    picture_url = re.search(r'<img id="bigImg" src="(.*?)"', content).group(1)
    picture = requests.get(picture_url).content
    suffix = re.sub(r'.*\.', '.', picture_url)
    with open('pic/' + str(count) + suffix, 'wb') as f:
      f.write(picture)

def spider(url, count):
    regex1 = r'<ul class="pic-list2clearfix">.*?</ul>'
    regex2 = r'<ul id="showImg".*?</ul>'
    urls = get_urls(url, regex1)
    for each_url in urls:
      picture_urls = get_urls(each_url, regex2)
      for each_picture_url in picture_urls:
            download_picture(each_picture_url, count)
            print 'Downloading picture ' + str(count)
            count += 1
    return count

def get_next_page_url(url):
    base_url = 'http://desk.zol.com.cn'
    content = requests.get(url).content
    tail = re.search(r'<a id="pageNext" href="(.*?)"', content).group(1)
    return base_url + tail

if __name__ == '__main__':
    url = 'http://desk.zol.com.cn/meinv/'
    count = 1
    count = spider(url, count)
    while True:
      key = raw_input('Input y/Y to continue download next page, or input other words to exit.')
      if re.match(r'Y', key, re.I):
            url = get_next_page_url(url)
            count = spider(url, count)
      else:
            exit()import os
import re
import requests

def get_urls(url, regex):
    urls = []
    base_url = 'http://desk.zol.com.cn'
    content = requests.get(url).content
    area = re.search(regex, content, re.S).group(0)
    tails = re.findall(r'href="(.*?)"', area)
    for tail in tails:
      urls.append(base_url + tail)
    return urls

def download_picture(url, count):
    target_dir = 'pic'
    if os.path.exists(target_dir):
      if not os.path.isdir(target_dir):
            os.remove(target_dir)
    else:
      os.mkdir(target_dir)
    content = requests.get(url).content
    picture_url = re.search(r'<img id="bigImg" src="(.*?)"', content).group(1)
    picture = requests.get(picture_url).content
    suffix = re.sub(r'.*\.', '.', picture_url)
    with open('pic/' + str(count) + suffix, 'wb') as f:
      f.write(picture)

def spider(url, count):
    regex1 = r'<ul class="pic-list2clearfix">.*?</ul>'
    regex2 = r'<ul id="showImg".*?</ul>'
    urls = get_urls(url, regex1)
    for each_url in urls:
      picture_urls = get_urls(each_url, regex2)
      for each_picture_url in picture_urls:
            download_picture(each_picture_url, count)
            print 'Downloading picture ' + str(count)
            count += 1
    return count

def get_next_page_url(url):
    base_url = 'http://desk.zol.com.cn'
    content = requests.get(url).content
    tail = re.search(r'<a id="pageNext" href="(.*?)"', content).group(1)
    return base_url + tail

if __name__ == '__main__':
    url = 'http://desk.zol.com.cn/meinv/'
    count = 1
    count = spider(url, count)
    while True:
      key = raw_input('Input y/Y to continue download next page, or input other words to exit.')
      if re.match(r'Y', key, re.I):
            url = get_next_page_url(url)
            count = spider(url, count)
      else:
            exit()import os
import re
import requests

def get_urls(url, regex):
    urls = []
    base_url = 'http://desk.zol.com.cn'
    content = requests.get(url).content
    area = re.search(regex, content, re.S).group(0)
    tails = re.findall(r'href="(.*?)"', area)
    for tail in tails:
      urls.append(base_url + tail)
    return urls

def download_picture(url, count):
    target_dir = 'pic'
    if os.path.exists(target_dir):
      if not os.path.isdir(target_dir):
            os.remove(target_dir)
    else:
      os.mkdir(target_dir)
    content = requests.get(url).content
    picture_url = re.search(r'<img id="bigImg" src="(.*?)"', content).group(1)
    picture = requests.get(picture_url).content
    suffix = re.sub(r'.*\.', '.', picture_url)
    with open('pic/' + str(count) + suffix, 'wb') as f:
      f.write(picture)

def spider(url, count):
    regex1 = r'<ul class="pic-list2clearfix">.*?</ul>'
    regex2 = r'<ul id="showImg".*?</ul>'
    urls = get_urls(url, regex1)
    for each_url in urls:
      picture_urls = get_urls(each_url, regex2)
      for each_picture_url in picture_urls:
            download_picture(each_picture_url, count)
            print 'Downloading picture ' + str(count)
            count += 1
    return count

def get_next_page_url(url):
    base_url = 'http://desk.zol.com.cn'
    content = requests.get(url).content
    tail = re.search(r'<a id="pageNext" href="(.*?)"', content).group(1)
    return base_url + tail

if __name__ == '__main__':
    url = 'http://desk.zol.com.cn/meinv/'
    count = 1
    count = spider(url, count)
    while True:
      key = raw_input('Input y/Y to continue download next page, or input other words to exit.')
      if re.match(r'Y', key, re.I):
            url = get_next_page_url(url)
            count = spider(url, count)
      else:
            exit()import os
import re
import requests

def get_urls(url, regex):
    urls = []
    base_url = 'http://desk.zol.com.cn'
    content = requests.get(url).content
    area = re.search(regex, content, re.S).group(0)
    tails = re.findall(r'href="(.*?)"', area)
    for tail in tails:
      urls.append(base_url + tail)
    return urls

def download_picture(url, count):
    target_dir = 'pic'
    if os.path.exists(target_dir):
      if not os.path.isdir(target_dir):
            os.remove(target_dir)
    else:
      os.mkdir(target_dir)
    content = requests.get(url).content
    picture_url = re.search(r'<img id="bigImg" src="(.*?)"', content).group(1)
    picture = requests.get(picture_url).content
    suffix = re.sub(r'.*\.', '.', picture_url)
    with open('pic/' + str(count) + suffix, 'wb') as f:
      f.write(picture)

def spider(url, count):
    regex1 = r'<ul class="pic-list2clearfix">.*?</ul>'
    regex2 = r'<ul id="showImg".*?</ul>'
    urls = get_urls(url, regex1)
    for each_url in urls:
      picture_urls = get_urls(each_url, regex2)
      for each_picture_url in picture_urls:
            download_picture(each_picture_url, count)
            print 'Downloading picture ' + str(count)
            count += 1
    return count

def get_next_page_url(url):
    base_url = 'http://desk.zol.com.cn'
    content = requests.get(url).content
    tail = re.search(r'<a id="pageNext" href="(.*?)"', content).group(1)
    return base_url + tail

if __name__ == '__main__':
    url = 'http://desk.zol.com.cn/meinv/'
    count = 1
    count = spider(url, count)
    while True:
      key = raw_input('Input y/Y to continue download next page, or input other words to exit.')
      if re.match(r'Y', key, re.I):
            url = get_next_page_url(url)
            count = spider(url, count)
      else:
            exit()import os
import re
import requests

def get_urls(url, regex):
    urls = []
    base_url = 'http://desk.zol.com.cn'
    content = requests.get(url).content
    area = re.search(regex, content, re.S).group(0)
    tails = re.findall(r'href="(.*?)"', area)
    for tail in tails:
      urls.append(base_url + tail)
    return urls

def download_picture(url, count):
    target_dir = 'pic'
    if os.path.exists(target_dir):
      if not os.path.isdir(target_dir):
            os.remove(target_dir)
    else:
      os.mkdir(target_dir)
    content = requests.get(url).content
    picture_url = re.search(r'<img id="bigImg" src="(.*?)"', content).group(1)
    picture = requests.get(picture_url).content
    suffix = re.sub(r'.*\.', '.', picture_url)
    with open('pic/' + str(count) + suffix, 'wb') as f:
      f.write(picture)

def spider(url, count):
    regex1 = r'<ul class="pic-list2clearfix">.*?</ul>'
    regex2 = r'<ul id="showImg".*?</ul>'
    urls = get_urls(url, regex1)
    for each_url in urls:
      picture_urls = get_urls(each_url, regex2)
      for each_picture_url in picture_urls:
            download_picture(each_picture_url, count)
            print 'Downloading picture ' + str(count)
            count += 1
    return count

def get_next_page_url(url):
    base_url = 'http://desk.zol.com.cn'
    content = requests.get(url).content
    tail = re.search(r'<a id="pageNext" href="(.*?)"', content).group(1)
    return base_url + tail

if __name__ == '__main__':
    url = 'http://desk.zol.com.cn/meinv/'
    count = 1
    count = spider(url, count)
    while True:
      key = raw_input('Input y/Y to continue download next page, or input other words to exit.')
      if re.match(r'Y', key, re.I):
            url = get_next_page_url(url)
            count = spider(url, count)
      else:
            exit()import os
import re
import requests

def get_urls(url, regex):
    urls = []
    base_url = 'http://desk.zol.com.cn'
    content = requests.get(url).content
    area = re.search(regex, content, re.S).group(0)
    tails = re.findall(r'href="(.*?)"', area)
    for tail in tails:
      urls.append(base_url + tail)
    return urls

def download_picture(url, count):
    target_dir = 'pic'
    if os.path.exists(target_dir):
      if not os.path.isdir(target_dir):
            os.remove(target_dir)
    else:
      os.mkdir(target_dir)
    content = requests.get(url).content
    picture_url = re.search(r'<img id="bigImg" src="(.*?)"', content).group(1)
    picture = requests.get(picture_url).content
    suffix = re.sub(r'.*\.', '.', picture_url)
    with open('pic/' + str(count) + suffix, 'wb') as f:
      f.write(picture)

def spider(url, count):
    regex1 = r'<ul class="pic-list2clearfix">.*?</ul>'
    regex2 = r'<ul id="showImg".*?</ul>'
    urls = get_urls(url, regex1)
    for each_url in urls:
      picture_urls = get_urls(each_url, regex2)
      for each_picture_url in picture_urls:
            download_picture(each_picture_url, count)
            print 'Downloading picture ' + str(count)
            count += 1
    return count

def get_next_page_url(url):
    base_url = 'http://desk.zol.com.cn'
    content = requests.get(url).content
    tail = re.search(r'<a id="pageNext" href="(.*?)"', content).group(1)
    return base_url + tail

if __name__ == '__main__':
    url = 'http://desk.zol.com.cn/meinv/'
    count = 1
    count = spider(url, count)
    while True:
      key = raw_input('Input y/Y to continue download next page, or input other words to exit.')
      if re.match(r'Y', key, re.I):
            url = get_next_page_url(url)
            count = spider(url, count)
      else:
            exit()import os
import re
import requests

def get_urls(url, regex):
    urls = []
    base_url = 'http://desk.zol.com.cn'
    content = requests.get(url).content
    area = re.search(regex, content, re.S).group(0)
    tails = re.findall(r'href="(.*?)"', area)
    for tail in tails:
      urls.append(base_url + tail)
    return urls

def download_picture(url, count):
    target_dir = 'pic'
    if os.path.exists(target_dir):
      if not os.path.isdir(target_dir):
            os.remove(target_dir)
    else:
      os.mkdir(target_dir)
    content = requests.get(url).content
    picture_url = re.search(r'<img id="bigImg" src="(.*?)"', content).group(1)
    picture = requests.get(picture_url).content
    suffix = re.sub(r'.*\.', '.', picture_url)
    with open('pic/' + str(count) + suffix, 'wb') as f:
      f.write(picture)

def spider(url, count):
    regex1 = r'<ul class="pic-list2clearfix">.*?</ul>'
    regex2 = r'<ul id="showImg".*?</ul>'
    urls = get_urls(url, regex1)
    for each_url in urls:
      picture_urls = get_urls(each_url, regex2)
      for each_picture_url in picture_urls:
            download_picture(each_picture_url, count)
            print 'Downloading picture ' + str(count)
            count += 1
    return count

def get_next_page_url(url):
    base_url = 'http://desk.zol.com.cn'
    content = requests.get(url).content
    tail = re.search(r'<a id="pageNext" href="(.*?)"', content).group(1)
    return base_url + tail

if __name__ == '__main__':
    url = 'http://desk.zol.com.cn/meinv/'
    count = 1
    count = spider(url, count)
    while True:
      key = raw_input('Input y/Y to continue download next page, or input other words to exit.')
      if re.match(r'Y', key, re.I):
            url = get_next_page_url(url)
            count = spider(url, count)
      else:
            exit()import os
import re
import requests

def get_urls(url, regex):
    urls = []
    base_url = 'http://desk.zol.com.cn'
    content = requests.get(url).content
    area = re.search(regex, content, re.S).group(0)
    tails = re.findall(r'href="(.*?)"', area)
    for tail in tails:
      urls.append(base_url + tail)
    return urls

def download_picture(url, count):
    target_dir = 'pic'
    if os.path.exists(target_dir):
      if not os.path.isdir(target_dir):
            os.remove(target_dir)
    else:
      os.mkdir(target_dir)
    content = requests.get(url).content
    picture_url = re.search(r'<img id="bigImg" src="(.*?)"', content).group(1)
    picture = requests.get(picture_url).content
    suffix = re.sub(r'.*\.', '.', picture_url)
    with open('pic/' + str(count) + suffix, 'wb') as f:
      f.write(picture)

def spider(url, count):
    regex1 = r'<ul class="pic-list2clearfix">.*?</ul>'
    regex2 = r'<ul id="showImg".*?</ul>'
    urls = get_urls(url, regex1)
    for each_url in urls:
      picture_urls = get_urls(each_url, regex2)
      for each_picture_url in picture_urls:
            download_picture(each_picture_url, count)
            print 'Downloading picture ' + str(count)
            count += 1
    return count

def get_next_page_url(url):
    base_url = 'http://desk.zol.com.cn'
    content = requests.get(url).content
    tail = re.search(r'<a id="pageNext" href="(.*?)"', content).group(1)
    return base_url + tail

if __name__ == '__main__':
    url = 'http://desk.zol.com.cn/meinv/'
    count = 1
    count = spider(url, count)
    while True:
      key = raw_input('Input y/Y to continue download next page, or input other words to exit.')
      if re.match(r'Y', key, re.I):
            url = get_next_page_url(url)
            count = spider(url, count)
      else:
            exit()import os
import re
import requests

def get_urls(url, regex):
    urls = []
    base_url = 'http://desk.zol.com.cn'
    content = requests.get(url).content
    area = re.search(regex, content, re.S).group(0)
    tails = re.findall(r'href="(.*?)"', area)
    for tail in tails:
      urls.append(base_url + tail)
    return urls

def download_picture(url, count):
    target_dir = 'pic'
    if os.path.exists(target_dir):
      if not os.path.isdir(target_dir):
            os.remove(target_dir)
    else:
      os.mkdir(target_dir)
    content = requests.get(url).content
    picture_url = re.search(r'<img id="bigImg" src="(.*?)"', content).group(1)
    picture = requests.get(picture_url).content
    suffix = re.sub(r'.*\.', '.', picture_url)
    with open('pic/' + str(count) + suffix, 'wb') as f:
      f.write(picture)

def spider(url, count):
    regex1 = r'<ul class="pic-list2clearfix">.*?</ul>'
    regex2 = r'<ul id="showImg".*?</ul>'
    urls = get_urls(url, regex1)
    for each_url in urls:
      picture_urls = get_urls(each_url, regex2)
      for each_picture_url in picture_urls:
            download_picture(each_picture_url, count)
            print 'Downloading picture ' + str(count)
            count += 1
    return count

def get_next_page_url(url):
    base_url = 'http://desk.zol.com.cn'
    content = requests.get(url).content
    tail = re.search(r'<a id="pageNext" href="(.*?)"', content).group(1)
    return base_url + tail

if __name__ == '__main__':
    url = 'http://desk.zol.com.cn/meinv/'
    count = 1
    count = spider(url, count)
    while True:
      key = raw_input('Input y/Y to continue download next page, or input other words to exit.')
      if re.match(r'Y', key, re.I):
            url = get_next_page_url(url)
            count = spider(url, count)
      else:
            exit()import os
import re
import requests

def get_urls(url, regex):
    urls = []
    base_url = 'http://desk.zol.com.cn'
    content = requests.get(url).content
    area = re.search(regex, content, re.S).group(0)
    tails = re.findall(r'href="(.*?)"', area)
    for tail in tails:
      urls.append(base_url + tail)
    return urls

def download_picture(url, count):
    target_dir = 'pic'
    if os.path.exists(target_dir):
      if not os.path.isdir(target_dir):
            os.remove(target_dir)
    else:
      os.mkdir(target_dir)
    content = requests.get(url).content
    picture_url = re.search(r'<img id="bigImg" src="(.*?)"', content).group(1)
    picture = requests.get(picture_url).content
    suffix = re.sub(r'.*\.', '.', picture_url)
    with open('pic/' + str(count) + suffix, 'wb') as f:
      f.write(picture)

def spider(url, count):
    regex1 = r'<ul class="pic-list2clearfix">.*?</ul>'
    regex2 = r'<ul id="showImg".*?</ul>'
    urls = get_urls(url, regex1)
    for each_url in urls:
      picture_urls = get_urls(each_url, regex2)
      for each_picture_url in picture_urls:
            download_picture(each_picture_url, count)
            print 'Downloading picture ' + str(count)
            count += 1
    return count

def get_next_page_url(url):
    base_url = 'http://desk.zol.com.cn'
    content = requests.get(url).content
    tail = re.search(r'<a id="pageNext" href="(.*?)"', content).group(1)
    return base_url + tail

if __name__ == '__main__':
    url = 'http://desk.zol.com.cn/meinv/'
    count = 1
    count = spider(url, count)
    while True:
      key = raw_input('Input y/Y to continue download next page, or input other words to exit.')
      if re.match(r'Y', key, re.I):
            url = get_next_page_url(url)
            count = spider(url, count)
      else:
            exit()import os
import re
import requests

def get_urls(url, regex):
    urls = []
    base_url = 'http://desk.zol.com.cn'
    content = requests.get(url).content
    area = re.search(regex, content, re.S).group(0)
    tails = re.findall(r'href="(.*?)"', area)
    for tail in tails:
      urls.append(base_url + tail)
    return urls

def download_picture(url, count):
    target_dir = 'pic'
    if os.path.exists(target_dir):
      if not os.path.isdir(target_dir):
            os.remove(target_dir)
    else:
      os.mkdir(target_dir)
    content = requests.get(url).content
    picture_url = re.search(r'<img id="bigImg" src="(.*?)"', content).group(1)
    picture = requests.get(picture_url).content
    suffix = re.sub(r'.*\.', '.', picture_url)
    with open('pic/' + str(count) + suffix, 'wb') as f:
      f.write(picture)

def spider(url, count):
    regex1 = r'<ul class="pic-list2clearfix">.*?</ul>'
    regex2 = r'<ul id="showImg".*?</ul>'
    urls = get_urls(url, regex1)
    for each_url in urls:
      picture_urls = get_urls(each_url, regex2)
      for each_picture_url in picture_urls:
            download_picture(each_picture_url, count)
            print 'Downloading picture ' + str(count)
            count += 1
    return count

def get_next_page_url(url):
    base_url = 'http://desk.zol.com.cn'
    content = requests.get(url).content
    tail = re.search(r'<a id="pageNext" href="(.*?)"', content).group(1)
    return base_url + tail

if __name__ == '__main__':
    url = 'http://desk.zol.com.cn/meinv/'
    count = 1
    count = spider(url, count)
    while True:
      key = raw_input('Input y/Y to continue download next page, or input other words to exit.')
      if re.match(r'Y', key, re.I):
            url = get_next_page_url(url)
            count = spider(url, count)
      else:
            exit()

koalary 发表于 2018-2-12 17:11:59

好棒

石头大大叔 发表于 2018-2-24 14:10:50

学习学习~

VIPLV 发表于 2018-2-25 16:30:31

求解

mlc123 发表于 2018-2-25 16:47:56

感谢分享

Echolulu 发表于 2018-2-25 18:06:26

k

来自他方 发表于 2018-2-25 18:07:02

学习。。。

不爱洗澡的阿毛 发表于 2018-2-25 18:11:00

谢谢分享

lii4562 发表于 2018-2-25 18:25:36

zhnega

keyi198707 发表于 2018-2-26 15:10:36

学习学习

查看完整版本: python简单爬虫实例-----爬取豆瓣妹子的照片