Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Python2.7下运行 #4

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Python2.7下运行 #4

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 7 additions & 2 deletions crawler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,14 +47,14 @@ def parse_url_to_html(url, name):
pattern = "(<img .*?src=\")(.*?)(\")"

def func(m):
if not m.group(3).startswith("http"):
if not m.group(2).startswith("http"):#这个group里的是2吧
rtn = m.group(1) + "http://www.liaoxuefeng.com" + m.group(2) + m.group(3)
return rtn
else:
return m.group(1)+m.group(2)+m.group(3)
html = re.compile(pattern).sub(func, html)
html = html_template.format(content=html)
html = html.encode("utf-8")
# html = html.encode("utf-8")#用的是Python2.7，把这个注释掉才能运行
with open(name, 'wb') as f:
f.write(html)
return name
Expand Down Expand Up @@ -110,6 +110,11 @@ def main():
urls = get_url_list()
file_name = u"liaoxuefeng_Python3_tutorial.pdf"
htmls = [parse_url_to_html(url, str(index) + ".html") for index, url in enumerate(urls)]
# htmls=[]
# for index,url in enumerate(urls):
# htmls.append(parse_url_to_html(url,str(index)))
# if index==10:
# break
save_pdf(htmls, file_name)

for html in htmls:
Expand Down