-
Notifications
You must be signed in to change notification settings - Fork 2.2k
Update NewsSpider.py #18
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Closed
Closed
Changes from all commits
Commits
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
89 changes: 32 additions & 57 deletions
NewsSpider/NewsSpider.py
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,61 +1,36 @@ | ||
| # -*- coding: utf-8 -*- | ||
| import os | ||
| import sys | ||
| import urllib2 | ||
| import requests | ||
| import re | ||
| from lxml import etree | ||
|
|
||
|
|
||
| def StringListSave(save_path, filename, slist): | ||
| if not os.path.exists(save_path): | ||
| os.makedirs(save_path) | ||
| path = save_path+"/"+filename+".txt" | ||
| with open(path, "w+") as fp: | ||
| for s in slist: | ||
| fp.write("%s\t\t%s\n" % (s[0].encode("utf8"), s[1].encode("utf8"))) | ||
|
|
||
| def Page_Info(myPage): | ||
| '''Regex''' | ||
| mypage_Info = re.findall(r'<div class="titleBar" id=".*?"><h2>(.*?)</h2><div class="more"><a href="(.*?)">.*?</a></div></div>', myPage, re.S) | ||
| return mypage_Info | ||
|
|
||
| def New_Page_Info(new_page): | ||
| '''Regex(slowly) or Xpath(fast)''' | ||
| # new_page_Info = re.findall(r'<td class=".*?">.*?<a href="(.*?)\.html".*?>(.*?)</a></td>', new_page, re.S) | ||
| # # new_page_Info = re.findall(r'<td class=".*?">.*?<a href="(.*?)">(.*?)</a></td>', new_page, re.S) # bugs | ||
| # results = [] | ||
| # for url, item in new_page_Info: | ||
| # results.append((item, url+".html")) | ||
| # return results | ||
| dom = etree.HTML(new_page) | ||
| new_items = dom.xpath('//tr/td/a/text()') | ||
| new_urls = dom.xpath('//tr/td/a/@href') | ||
| assert(len(new_items) == len(new_urls)) | ||
| return zip(new_items, new_urls) | ||
|
|
||
| def Spider(url): | ||
| i = 0 | ||
| print "downloading ", url | ||
| myPage = requests.get(url).content.decode("gbk") | ||
| # myPage = urllib2.urlopen(url).read().decode("gbk") | ||
| myPageResults = Page_Info(myPage) | ||
| save_path = u"网易新闻抓取" | ||
| filename = str(i)+"_"+u"新闻排行榜" | ||
| StringListSave(save_path, filename, myPageResults) | ||
| i += 1 | ||
| for item, url in myPageResults: | ||
| print "downloading ", url | ||
| new_page = requests.get(url).content.decode("gbk") | ||
| # new_page = urllib2.urlopen(url).read().decode("gbk") | ||
| newPageResults = New_Page_Info(new_page) | ||
| filename = str(i)+"_"+item | ||
| StringListSave(save_path, filename, newPageResults) | ||
| i += 1 | ||
| from bs4 import BeautifulSoup | ||
|
|
||
|
|
||
| def save_to_file(file_path, file_name, data): | ||
| if not os.path.exists(file_path): | ||
| os.makedirs(file_path) | ||
| path = os.path.join(file_path, file_name + '.txt') | ||
| with open(path, "w", encoding='utf-8') as file: | ||
| for item in data: | ||
| file.write(item + '\n') | ||
|
|
||
|
|
||
| def get_page_info(page_content): | ||
| soup = BeautifulSoup(page_content, 'html.parser') | ||
| title = soup.find('h2', class_='titleBar').get_text(strip=True) | ||
| more_link = soup.find('div', class_='more').find('a')['href'] | ||
| return title, more_link | ||
|
|
||
|
|
||
| def spider(url): | ||
| response = requests.get(url) | ||
| response.encoding = 'gbk' | ||
| page_content = response.text | ||
| title, more_link = get_page_info(page_content) | ||
| print(f"Title: {title}") | ||
| print(f"More Link: {more_link}") | ||
| # Save the title and more link to a file | ||
| save_to_file('news', 'news_info', [title, more_link]) | ||
|
|
||
|
|
||
| if __name__ == '__main__': | ||
| print "start" | ||
| start_url = "http://news.163.com/rank/" | ||
| Spider(start_url) | ||
| print "end" | ||
| start_url = "http://example.com/start-page" | ||
| print("Start") | ||
| spider(start_url) | ||
| print("End") |
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.