def parse_movie_info(self, page, page_url):
try:
content = self.random_delay_get(page_url).content
file_name = self._get_temp_filename()
with open(file_name, "w") as fd:
fd.write(content)
movie_urls = []
with open(file_name, "r") as fd:
lines = fd.readlines()
for line in lines:
line = line.strip()
if not "ulink" in line:
continue
dom = BeautifulSoup(line, "lxml")
movie_urls.append(dom.body.a["href"])
os.remove(file_name)
url_pre = page_url.split("/html", 1)[0]
log.info("url_pre: %s", url_pre)
for movie_url in movie_urls:
movie_url = "".join([url_pre, movie_url])
self.parse_movie_detail_info(movie_url)
except Exception:
log.error("parse_movie_info failed! page: %s, page_url: %s",
page, page_url, exc_info=True)
def parse_movie_list(self, movie_type, url):
try:
if not url.startswith("http"):
url = "".join([self.base_url, url])
url_pre = url.rsplit("/", 1)[0]
log.info("url_pre: %s", url_pre)
content = self.random_delay_get(url).content
page_urls = self._parse_list(content)
for page, page_url in page_urls:
page_url = "/".join([url_pre, page_url])
self.parse_movie_info(page, page_url)
except Exception:
log.error("parse_movie_list failed! movie_type: %s, url: %s",
movie_type, url, exc_info=True)
def _parse_list(self, content):
page_urls = []
file_name = self._get_temp_filename()
with open(file_name, "w") as fd:
fd.write(content)
with open(file_name, "r") as fd:
for line in fd.readlines():
line = line.strip()
if not "option" in line:
continue
try:
tag_option = BeautifulSoup(line, "lxml")
page = int(tag_option.text)
url = tag_option.body.option["value"]
log.info("page: %s, url: %s", page, url)
page_urls.append([page, url])
except:
pass
os.remove(file_name)
return page_urls
def parse_index(self):
index_content = self.sess.get(self.base_url).content
dom = BeautifulSoup(index_content, "lxml")
tag_div_menu = dom.find_all("div", {"id": "menu"})
menu_urls = {}
tag_a = tag_div_menu[0].find_all("a")
for url in tag_a:
menu_urls[url.text] = url["href"]
log.info("movie_type: %s, url: %s", url.text, url["href"])
log.info(menu_urls)
for movie_type, url in menu_urls.iteritems():
if url in ["#", "index.html"]:
log.info("ignore movie_type: %s, url: %s", url.text, url["href"])
continue
self.parse_movie_list(movie_type, url)