guanjihuan/guanjihuan.com
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
guanjihuan
2022-10-27 16:57:22 +08:00
parent 6325f03ed9
commit 49e3efd12c
5 changed files with 11 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
language_learning/2021.11.17_zhihu/nature_physics.py
View File

@@ -27,11 +27,11 @@ for article in all_article:
href = 'https://www.nature.com'+ href href = 'https://www.nature.com'+ href
if href not in match_href and re.search('\?', href)==None: # 链接不重复 if href not in match_href and re.search('\?', href)==None: # 链接不重复
match_href.append(href) match_href.append(href)
f.write('<p><a target=\"_blank\" href=\"') f.write('<li><a target=\"_blank\" href=\"')
f.write(href) # 文章链接 f.write(href) # 文章链接
f.write('\">') f.write('\">')
f.write(a_tag.get_text()) f.write(a_tag.get_text())
f.write('</a>&nbsp;&nbsp;') f.write('</a>&nbsp;&nbsp;')
time = article.find('time', {"class": "c-meta__item c-meta__item--block-at-lg"}).get_text() time = article.find('time', {"class": "c-meta__item c-meta__item--block-at-lg"}).get_text()
f.write(time+'</p>') f.write(time+'</li>')
f.close() f.close()

4
language_learning/2021.11.17_zhihu/physics_magazine.py
View File

@@ -26,11 +26,11 @@ for article in all_articles:
href = 'https://physics.aps.org'+ href href = 'https://physics.aps.org'+ href
if href not in match_href: if href not in match_href:
match_href.append(href) match_href.append(href)
f.write('<p><a target=\"_blank\" href=\"') f.write('<li><a target=\"_blank\" href=\"')
f.write(href) # 文章链接 f.write(href) # 文章链接
f.write('\">') f.write('\">')
f.write(a_tag.get_text()) f.write(a_tag.get_text())
f.write('</a>&nbsp;&nbsp;') f.write('</a>&nbsp;&nbsp;')
time = article.find('time', {"class": "feed-item-date"}).get_text() time = article.find('time', {"class": "feed-item-date"}).get_text()
f.write(time+'</p>') f.write(time+'</li>')
f.close() f.close()

4
language_learning/2021.11.17_zhihu/prb.py
View File

@@ -31,12 +31,12 @@ for loop in range(1):
href = 'https://journals.aps.org'+ href href = 'https://journals.aps.org'+ href
if href not in match_href and re.search('\?', href)==None: # 链接不重复 if href not in match_href and re.search('\?', href)==None: # 链接不重复
match_href.append(href) match_href.append(href)
f.write('<p><a target=\"_blank\" href=\"') f.write('<li><a target=\"_blank\" href=\"')
f.write(href) # 文章链接 f.write(href) # 文章链接
f.write('\">') f.write('\">')
f.write(a_tag.get_text()) f.write(a_tag.get_text())
f.write('</a>&nbsp;&nbsp;') f.write('</a>&nbsp;&nbsp;')
info = article.find('h6', {"class": "pub-info"}).get_text() info = article.find('h6', {"class": "pub-info"}).get_text()
f.write(re.findall('– Published .*', info, re.S)[0][12:]+'</p>') f.write(re.findall('– Published .*', info, re.S)[0][12:]+'</li>')
f.close() f.close()

4
language_learning/2021.11.17_zhihu/prl.py
View File

@@ -31,12 +31,12 @@ for loop in range(1):
href = 'https://journals.aps.org'+ href href = 'https://journals.aps.org'+ href
if href not in match_href and re.search('\?', href)==None: # 链接不重复 if href not in match_href and re.search('\?', href)==None: # 链接不重复
match_href.append(href) match_href.append(href)
f.write('<p><a target=\"_blank\" href=\"') f.write('<li><a target=\"_blank\" href=\"')
f.write(href) # 文章链接 f.write(href) # 文章链接
f.write('\">') f.write('\">')
f.write(a_tag.get_text()) f.write(a_tag.get_text())
f.write('</a>&nbsp;&nbsp;') f.write('</a>&nbsp;&nbsp;')
info = article.find('h6', {"class": "pub-info"}).get_text() info = article.find('h6', {"class": "pub-info"}).get_text()
f.write(re.findall('– Published.*', info, re.S)[0][12:]+'</p>') f.write(re.findall('– Published.*', info, re.S)[0][12:]+'</li>')
f.close() f.close()

6
language_learning/2021.11.17_zhihu/zhihu.py
View File

@@ -15,7 +15,7 @@ day = datetime.datetime.now().day
# 获取链接 # 获取链接
match_href = [] match_href = []
# 由于没有模拟登录知乎，因此只能爬取到最新的两篇文章 # 由于没有模拟登录知乎，因此只能爬取到最新的两篇文章
authors = ["https://www.zhihu.com/people/g3508/posts", # Guan authors = ["https://www.zhihu.com/people/guanjihuan/posts", # Guan
] ]
for i0 in range(len(authors)): for i0 in range(len(authors)):
start_link = authors[i0] start_link = authors[i0]
@@ -47,7 +47,7 @@ for href in match_href_new:
html = urlopen(href).read().decode('utf-8') # 打开文章链接 html = urlopen(href).read().decode('utf-8') # 打开文章链接
soup = BeautifulSoup(html, features='lxml') # 放入soup中 soup = BeautifulSoup(html, features='lxml') # 放入soup中
title = soup.title # 文章标题 title = soup.title # 文章标题
f.write('<p><a target=\"_blank\" href=\"') f.write('<li><a target=\"_blank\" href=\"')
f.write(str(href)) # 文章链接 f.write(str(href)) # 文章链接
f.write('\">') f.write('\">')
f.write(str(title.get_text()[:-5])) f.write(str(title.get_text()[:-5]))
@@ -55,7 +55,7 @@ for href in match_href_new:
author = soup.find("span", {"class": "UserLink AuthorInfo-name"}) author = soup.find("span", {"class": "UserLink AuthorInfo-name"})
f.write(str(author.get_text()+'&nbsp;&nbsp;')) f.write(str(author.get_text()+'&nbsp;&nbsp;'))
post_time = soup.find("div", {"class" : "ContentItem-time"}) post_time = soup.find("div", {"class" : "ContentItem-time"})
f.write(str(post_time.get_text()[4:-6])+'</p>') f.write(str(post_time.get_text()[4:-6])+'</li>')
except: except:
pass pass
f.close() f.close()