try:
link = link.get("href")
mostviewed_linklist = parserfunctions.linklist_actions(
link, mostviewed_linklist)
except:
pass
except:
message = "Failed at getting MV link list"
seriousness = 2
parserfunctions.error_log_entry(cur, conn, mysql_log_name,
curr_time, pubshort, homepage,
seriousness, message)
#continue
try:
pop_top_5_links = parserfunctions.get_top_5_list_links(
mostviewed_linklist)
except:
pop_top_5_links = []
message = "Failed to get a POP link"
seriousness = 2
parserfunctions.error_log_entry(cur, conn, mysql_log_name,
curr_time, pubshort, homepage,
seriousness, message)
#continue
##### Get Most Prominent Items
### LAYOUT #1
if layout == 1:
try: # Carousel Stories -- although carousel is randomized in browser, it is static in the code, so we prioritize the code
prominence_1to3 = [
link.find("a", href=link_pattern)
try:
link = link.get("href")
mostviewed_linklist = parserfunctions.linklist_actions(
link, mostviewed_linklist)
except:
pass
except:
message = "Failed at getting MV link list"
seriousness = 2
parserfunctions.error_log_entry(cur, conn, mysql_log_name, curr_time,
pubshort, homepage, seriousness,
message)
#continue
try:
pop_top_5_links = parserfunctions.get_top_5_list_links(
mostviewed_linklist)
except:
pop_top_5_links = []
message = "Failed to get a POP link"
seriousness = 2
parserfunctions.error_log_entry(cur, conn, mysql_log_name, curr_time,
pubshort, homepage, seriousness,
message)
#continue
###### Get list of links on the page
try:
document_soup_on_page = parserfunctions.soupify(document_data)
except:
message = "Failed to resoupify the document"
seriousness = 1
mostviewed_1to5 = [link.find("a", href=re.compile(pattern)) for link in document_soup.find("div", id="mostreademailed").find_all("li")] # ID is most e-mailed, but page states most read
mostviewed_linklist = []
for link in mostviewed_1to5:
try:
link = link.get("href")
mostviewed_linklist = parserfunctions.linklist_actions(link, mostviewed_linklist)
except:
pass
except:
message = "Failed at getting MV link list"
seriousness = 2
parserfunctions.error_log_entry(cur, conn, mysql_log_name, curr_time, pubshort, homepage, seriousness, message)
#continue
try:
pop_top_5_links = parserfunctions.get_top_5_list_links(mostviewed_linklist)
except:
pop_top_5_links = []
message = "Failed to get a POP link"
seriousness = 2
parserfunctions.error_log_entry(cur, conn, mysql_log_name, curr_time, pubshort, homepage, seriousness, message)
#continue
##### Get Most Prominent Items
### LAYOUT #1
if layout == 1:
try: # Lead story
prominence_1 = [link.find("a", href=re.compile(pattern)) for link in document_soup.find("div", class_=re.compile("co_3colvisual|co_2colvisual|co_2_5colvisual")).find_all(re.compile("h1|h2|h3|h4"))]
prominence_linklist = []
for link in prominence_1:
try:
